Last active
August 29, 2015 14:00
-
-
Save pyrocat101/11205476 to your computer and use it in GitHub Desktop.
Regex 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
(defn syntax-error [] | |
(throw (ex-info "Syntax Error" {}))) | |
(declare alt then star prime) | |
(defn expect [s c] | |
(if (not= (first s) c) | |
(syntax-error) | |
(rest s))) | |
(defn alt [s] | |
(let [[a s] (then s)] | |
(if (= (first s) "|") | |
(let [[b s*] (alt (rest s))] | |
[(list :alt a b) s*]) | |
[a s]))) | |
(defn then [s] | |
(let [[c s] (star s)] | |
(if (or (= (first s) "(") | |
(re-matches #"\w" (first s))) | |
(let [[d s*] (then s)] | |
[(list :then c d) s*]) | |
[c s]))) | |
(defn star [s] | |
(let [[p s] (prime s) | |
P [p]] | |
(println p) | |
(if (= (first s) "*") | |
[(cons :star P) (rest s)] | |
[(first P) s]))) | |
(defn prime [s] | |
(if (re-matches #"\w" (first s)) | |
(do | |
[(list :literal (first s)) (rest s)]) | |
(do | |
(let [s* (expect s "(") | |
[r s**] (alt s*) | |
s*** (expect s** ")")] | |
[r s***])))) | |
(defn parse-regex [s] | |
(let [s (map str (lazy-cat s "\x00")) | |
[tree s*] (alt s)] | |
(if-not (= (first s*) "\x00") | |
(syntax-error) | |
tree))) | |
(parse-regex "a") | |
(parse-regex "abc") | |
(parse-regex "(ab)") | |
(parse-regex "(ab)*") | |
(parse-regex "(ab)*(c|d)*(e|f)") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment