Created
January 6, 2015 16:36
-
-
Save ecounysis/3d007c72c96755f003c1 to your computer and use it in GitHub Desktop.
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
module Parsing = | |
//type Char = string | |
//type Str = string | |
type Remaining = string | |
type Result<'a> = Success of 'a * Remaining | |
| Failure | |
type Parser<'a> = string -> Result<'a> | |
(* | |
type ParserBuilder() = | |
member this.Bind ((x : Parser<'a>), (rest : Remaining -> Parser<'a>)) = | |
match x with | |
| Success (x, r) -> rest r | |
| Failure -> fun (inp : Str) -> Failure | |
member this.Return (x : 'a) = fun (inp : Remaining) -> Success (x, inp) | |
let parseX = ParserBuilder() | |
*) | |
let ret (v : 'a) : Parser<'a> = fun (inp : string) -> Success (v, inp) | |
let failure : Parser<'a> = fun (inp : string) -> Failure | |
let parse (p : Parser<'a>) (inp : string) : Result<'a> = p inp | |
let (|First|) (s:string) = | |
if s.Length > 0 | |
then s.Substring(0, 1) | |
else "" | |
let (|Rest|) (s:string) = | |
if s.Length > 1 | |
then s.Substring(1) | |
else "" | |
let (|First2|) (s:string) = | |
if s.Length > 1 | |
then s.Substring(0, 2) | |
else "" | |
let (|Rest2|) (s:string) = | |
if s.Length > 2 | |
then s.Substring(2) | |
else "" | |
let item : Parser<string> = fun inp -> match inp with | |
| "" -> Failure | |
| First f & Rest r -> Success (f, r) | |
let (>>=) (p : Parser<'a>) (f : 'a -> Parser<'b>) : Parser<'b> = | |
fun inp -> match parse p inp with | |
| Failure -> Failure | |
| Success (v, out) -> parse (f v) out | |
let (+++) p q = fun inp -> match parse p inp with | |
| Failure -> parse q inp | |
| Success (v, out) -> Success (v, out) | |
let sat (p : string -> bool) : Parser<string> = | |
item >>= fun x -> | |
if p x then ret x else failure | |
(* | |
let eof : Parser<string> = | |
sat (fun x -> x.Length = 0) | |
let sat2 (p : Char -> bool) : Parser<string> = | |
parseX { | |
let! x = item | |
return (if p x then x else "") | |
} | |
*) | |
let isDigit (x:string) : bool = | |
if not (x.Length = 1) | |
then false | |
else | |
let digits = ['0'..'9'] | |
List.exists (fun ch -> ch = x.ToCharArray().[0]) digits | |
let digit = sat isDigit | |
let char (x:string) : Parser<string> = sat (fun y -> y = x) | |
let rec str (x:string) : Parser<string> = | |
match x with | |
| "" -> failure | |
| First x & Rest xs -> char x >>= fun _ -> | |
str xs >>= fun _ -> | |
ret (x+xs) | |
let comma = char "," | |
let quote = char "\"" | |
let quoteComma = quote >>= fun _ -> | |
comma >>= fun _ -> | |
ret "" | |
let twoQuote = quote >>= fun x -> | |
quote >>= fun y -> | |
ret (x+y) | |
let rec many p = many1 p +++ ret "" | |
and many1 p = p >>= fun v -> | |
many p >>= fun vs -> | |
ret (v + vs) | |
let notQuote = | |
sat (fun x -> not (x = "\"")) | |
let notComma = | |
sat (fun x -> not (x = ",")) | |
let tilEndUqField = | |
notComma >>= fun x -> | |
ret x | |
let uqField = | |
tilEndUqField >>= fun data -> | |
ret data | |
let rest = | |
many (sat (fun _ -> true)) | |
(* | |
let quoteComma (x:string) : Parser<Str> = | |
match x with | |
| "" -> ret "" | |
| First f & Rest r when f = "\"" -> | |
match r with | |
| First f2 & Rest r2 when f2 = | |
//| First2 f & Rest2 r -> if f = "\"," then ret f else ret | |
*) | |
let qField = | |
quote >>= fun _ -> | |
(many notQuote) >>= fun inside -> | |
ret inside | |
// q,"we,r","we,""ee"",,y" | |
// q | |
// we,r | |
// we,"ee",,y | |
//let csv (st:string) : Parser<string list> = |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment