Last active
December 1, 2019 07:22
-
-
Save abhayarawal/fa1a3f2d2691c091552bd2b69543d06f to your computer and use it in GitHub Desktop.
html parser
This file contains 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
| // https://bodil.lol/parser-combinators/ | |
| #[derive(Debug, Clone, PartialEq, Eq)] | |
| struct Element { | |
| name: String, | |
| attributes: Vec<(String, String)>, | |
| children: Vec<Element>, | |
| } | |
| type ParseResult<'a, Output> = Result<(&'a str, Output), &'a str>; | |
| trait Parser<'a, Output> { | |
| fn parse(&self, input: &'a str) -> ParseResult<'a, Output>; | |
| } | |
| impl<'a, F, Output> Parser<'a, Output> for F | |
| where | |
| F: Fn(&'a str) -> ParseResult<Output> | |
| { | |
| fn parse(&self, input: &'a str) -> ParseResult<'a, Output> { | |
| self(input) | |
| } | |
| } | |
| fn match_literal<'a>(expected: &'a str) -> impl Fn(&str) -> ParseResult<()> + 'a { | |
| move |input| { | |
| if input.starts_with(expected) { | |
| return Ok((&input[expected.len()..], ())); | |
| } | |
| Err(input) | |
| } | |
| } | |
| fn identifier(input: &str) -> ParseResult<String> { | |
| let mut matched = String::new(); | |
| let mut chars = input.chars(); | |
| match chars.next() { | |
| Some(next) if next.is_alphabetic() => matched.push(next), | |
| _ => return Err(input), | |
| } | |
| while let Some(next) = chars.next() { | |
| if next.is_alphanumeric() || next == '-' { | |
| matched.push(next); | |
| } else { | |
| break; | |
| } | |
| } | |
| let next_index = matched.len(); | |
| Ok((&input[next_index..], matched)) | |
| } | |
| fn pair<P1, P2, R1, R2>(parser1: P1, parser2: P2) -> impl Fn(&str) -> ParseResult<(R1, R2)> | |
| where | |
| P1: Fn(&str) -> Result<(&str, R1), &str>, | |
| P2: Fn(&str) -> Result<(&str, R2), &str>, | |
| { | |
| move |input| match parser1(input) { | |
| Ok((next_input, result1)) => match parser2(next_input) { | |
| Ok((final_input, result2)) => Ok((final_input, (result1, result2))), | |
| Err(err) => Err(err), | |
| }, | |
| Err(err) => Err(err), | |
| } | |
| } | |
| fn map<P, F, A, B>(parser: P, map_fn: F) -> impl Fn(&str) -> Result<(&str, A), &str> | |
| where | |
| P: Fn(&str) -> Result<(&str, B), &str>, | |
| F: Fn(B) -> A | |
| { | |
| move |input| match parser(input) { | |
| Ok((next_input, result)) => Ok((next_input, map_fn(result))), | |
| Err(err) => Err(err), | |
| } | |
| } | |
| fn main() {} | |
| #[cfg(test)] | |
| mod tests { | |
| use super::*; | |
| #[test] | |
| fn text_expected() { | |
| let parser = match_literal("hiya"); | |
| assert_eq!(parser("hiya there"), Ok((" there", ()))); | |
| assert_eq!(parser("hi there"), Err("hi there")); | |
| } | |
| #[test] | |
| fn test_identifier() { | |
| assert_eq!(identifier("small-span"), Ok(("", "small-span".to_string()))); | |
| assert_eq!(identifier("h2 span"), Ok((" span", "h2".to_string()))); | |
| assert_eq!(identifier("!span"), Err("!span")); | |
| } | |
| #[test] | |
| fn test_pair() { | |
| let tag = pair(match_literal("<"), identifier); | |
| assert_eq!(Ok((">", ((), "span".to_string()))), tag("<span>")); | |
| assert_eq!(Err("span>"), tag("span>")); | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment