Created
July 3, 2018 21:24
-
-
Save king1600/18efe381cd2b684566b26fa71b19c92b to your computer and use it in GitHub Desktop.
(Language) Lexer Generator written in pony
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
use "regex" | |
class Rule[T] | |
let name: String | |
let regex: String | |
let _create: {(String): T^} | |
new create(name': String, regex': String, make: {(String): T^}) => | |
name = name' | |
regex = regex' | |
_create = make | |
fun from(text: String): T^ => | |
_create(consume text) | |
class Lexer[T] | |
let _regex: Regex | |
let rules: Array[Rule[T]] | |
new create(rules': Array[Rule[T]]) ? => | |
let rule_list = Array[String](rules'.size()) | |
for rule in rules'.values() do | |
rule_list.push( | |
(recover String(rule.name.size()) end) | |
.>append("(?<").>append(rule.name).>push('>') | |
.>append(rule.regex).>push(')')) | |
end | |
_regex = Regex("|".join(rule_list.values()))? | |
rules = consume rules' | |
fun lex(input: String): LexemeIter[T]^ => | |
LexemeIter[T](this, _regex.matches(consume input)) | |
class LexemeIter[T] is Iterator[T] | |
let _lexer: Lexer[T] box | |
let _iter: MatchIterator | |
new create(lexer: Lexer[T] box, iter: MatchIterator) => | |
_iter = iter | |
_lexer = lexer | |
fun ref has_next(): Bool => | |
_iter.has_next() | |
fun ref next(): T^ ? => | |
let m = _iter.next()? | |
for rule in _lexer.rules.values() do | |
try return rule.from(m.find(rule.name)?) end | |
end | |
error |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment