Last active
August 29, 2015 14:26
-
-
Save seoh/41007ef9b0477cacad30 to your computer and use it in GitHub Desktop.
Simple Monadic Parser using JavaScript
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
// https://www.cs.nott.ac.uk/~gmh/monparsing.pdf | |
// | |
// type Parser[T] = String -> [(T, String)] | |
// | |
/** lookahead token | |
* | |
* Parser -> Parser | |
*/ | |
const ahead = p => (str) => | |
p(str) ? ['', str] : []; | |
/** consume token | |
* | |
* Parser -> Parser | |
*/ | |
const satisfy = p => (str) => | |
p(str) ? [str[0], str.substr(1)] : []; | |
/** compose funtions, not used in this | |
* | |
* [(a -> a)] -> (a -> a) | |
*/ | |
const compose = (...fns) => (arg) => | |
fns.reverse().reduce((r,fn) => fn.apply(null, [r]), arg); | |
/** fallback | |
* | |
* (Parser, Parser) -> Parser | |
*/ | |
const or = (pa, pb) => (str) => { | |
const r = pa(str); | |
if(r.length > 0) return r; | |
else return pb(str); | |
}; | |
/** sequencial | |
* | |
* (Parser, Parser) -> Parser | |
*/ | |
const and = (pa, pb) => (str) => { | |
const ra = pa(str); | |
if(ra.length === 0) return []; | |
const rb = pb(ra[1]); | |
if(rb.length === 0) return []; | |
return [ra[0] + rb[0], rb[1]]; | |
}; | |
/** monoid zero | |
* | |
* Parser | |
*/ | |
const mzero = (str) => ['', str]; | |
/** consume zero or more times token | |
* | |
* Parser -> Parser | |
*/ | |
const many = (p) => (str) => { | |
const ra = p(str); | |
if(ra.length === 0) return ra; | |
const rb = or(many(p), mzero)(ra[1]); | |
return [ra[0] + rb[0], rb[1]]; | |
}; | |
//----------------------------------------------------------------------------// | |
const chr = ahead(str => str.length > 0); | |
const upper = and(chr, satisfy(ch => 'A' <= ch[0] && ch[0] <= 'Z')); | |
const lower = and(chr, satisfy(ch => 'a' <= ch[0] && ch[0] <= 'z')); | |
const digit = and(chr, satisfy(ch => '0' <= ch[0] && ch[0] <= '9')); | |
/** | |
* - Tokenizer | |
* | |
* atom = upper lower | upper | |
* amount = digit amount | digit | empty | |
* | |
* | |
* - Lexer | |
* | |
* mole = homo mole | mole | |
* homo = atom amount | atom | |
* | |
*/ | |
const atom = or(and(upper, lower), upper); | |
const amount = many(digit); | |
const homo = or(and(atom, amount), atom); | |
const mole = many(homo); | |
const parse = (p) => (str) => or(p, mzero)(str)[0]; | |
console.log(parse(mole)("H2O")); | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment