(* ===========================================================================
   Jolt reader grammar (EBNF)
   ===========================================================================

   This grammar specifies the surface syntax accepted by Jolt's reader
   (src/jolt/reader.janet) — the text that `read`/`parse-string`/`load-string`
   turn into data/forms. It is the syntactic half of Jolt's contract; the
   behavioural half lives in test/spec/. Where Jolt diverges from Clojure the
   difference is called out in a comment.

   Notation (ISO-ish EBNF):
     =           definition          |   alternation
     ,           concatenation       ( )  grouping
     [ x ]       optional (0 or 1)   { x }  repetition (0 or more)
     "x" 'x'     terminal            (* *)  comment
     ? x ?       informal/char-class terminal

   A source file is a sequence of forms; evaluation is form-by-form.
   =========================================================================== *)

file            = { ws | form } ;

(* --------------------------------------------------------------------------
   Whitespace, separators and comments
   -------------------------------------------------------------------------- *)

ws              = { whitespace-char | comment | discard } ;
whitespace-char = " " | "\t" | "\n" | "\r" | "," ;   (* comma is whitespace *)
comment         = ";" , { ? any char except "\n" ? } , [ "\n" ] ;
discard         = "#_" , ws , form ;                 (* read then drop next form *)

(* --------------------------------------------------------------------------
   Forms
   -------------------------------------------------------------------------- *)

form            = scalar
                | collection
                | reader-macro
                | dispatch ;

scalar          = nil | boolean | number | string | character
                | keyword | symbol ;

collection      = list | vector | map ;

(* --------------------------------------------------------------------------
   Atoms / scalars
   -------------------------------------------------------------------------- *)

nil             = "nil" ;
boolean         = "true" | "false" ;

(* Numbers. Jolt accepts Clojure's numeric literal syntaxes, but — since Jolt
   numbers are Janet ints/doubles — it has no distinct bignum, ratio or
   BigDecimal types: the BigInt suffix N and BigDecimal suffix M are read as the
   plain number, a ratio a/b is read as its double quotient, and radixed
   integers are computed by base. The symbolic floats ##Inf/##-Inf/##NaN are
   also read. (No octal-with-leading-0 literal.) *)
number          = symbolic-value
                | [ sign ] , ( radix-int | ratio | hex-int | decimal ) ;
sign            = "+" | "-" ;
integer         = digit , { digit } ;
hex-int         = "0" , ( "x" | "X" ) , hex-digit , { hex-digit } , [ "N" ] ;
radix-int       = integer , ( "r" | "R" ) , alnum , { alnum } ; (* base 2..36: 2r1010, 16rFF, 36rZ *)
ratio           = integer , "/" , integer ;                     (* read as a double quotient *)
decimal         = integer , [ "." , digit , { digit } ] , [ exponent ] , [ num-suffix ] ;
exponent        = ( "e" | "E" ) , [ sign ] , digit , { digit } ;
num-suffix      = "N" | "M" ;          (* BigInt / BigDecimal in Clojure; plain number in Jolt *)
symbolic-value  = "##Inf" | "##-Inf" | "##NaN" ;
digit           = "0".."9" ;
hex-digit       = digit | "a".."f" | "A".."F" ;
alnum           = digit | "a".."z" | "A".."Z" ;

(* Strings: double-quoted with backslash escapes. *)
string          = '"' , { string-char } , '"' ;
string-char     = ? any char except '"' and "\" ? | escape ;
escape          = "\" , ( "n" | "t" | "r" | "\" | '"' | ? other ? ) ;

(* Characters: \x, a named char, or \uNNNN / \oNNN. *)
character       = "\" , ( char-name | ? any single char ? ) ;
char-name       = "newline" | "space" | "tab" | "return"
                | "formfeed" | "backspace" | "nul"
                | "u" , hex-digit , hex-digit , hex-digit , hex-digit
                | "o" , octal-digit , { octal-digit } ;
octal-digit     = "0".."7" ;

(* Keywords: :name, :ns/name, or auto-resolved ::name. *)
keyword         = "::" , sym-token            (* auto-resolved to current ns *)
                | ":" , sym-token ;

(* Symbols: a token of symbol-constituent chars not parsed as a number. A "/"
   separates an optional namespace from the name. *)
symbol          = sym-token ;
sym-token       = sym-start , { sym-constituent } ;
sym-start       = sym-constituent - ( digit ) ;     (* not a leading digit *)
sym-constituent = letter | digit
                | "*" | "+" | "!" | "_" | "-" | "?" | "." | "<" | ">"
                | "=" | "&" | "|" | "$" | "%" | "/" ;
letter          = "a".."z" | "A".."Z" ;

(* --------------------------------------------------------------------------
   Collections
   -------------------------------------------------------------------------- *)

list            = "(" , { ws | form } , ")" ;   (* -> a Clojure list *)
vector          = "[" , { ws | form } , "]" ;   (* -> a persistent vector *)
map             = "{" , { ws | map-entry } , "}" ;
map-entry       = form , ws , form ;            (* an even number of forms *)

(* --------------------------------------------------------------------------
   Reader macros (prefix sugar). Each expands to a 2-element form
   (op operand), e.g. 'x -> (quote x), @a -> (deref a).
   -------------------------------------------------------------------------- *)

reader-macro    = quote | syntax-quote | unquote | unquote-splice
                | deref | metadata ;

quote           = "'"  , form ;        (* (quote form)            *)
syntax-quote    = "`"  , form ;        (* (syntax-quote form)     *)
unquote-splice  = "~@" , form ;        (* (unquote-splicing form) *)
unquote         = "~"  , form ;        (* (unquote form)          *)
deref           = "@"  , form ;        (* (deref form)            *)
metadata        = "^"  , meta-form , ws , form ;   (* attach metadata to form *)
meta-form       = map | keyword | symbol | string ;
(* Normalized like Clojure: a symbol or string is a type hint -> {:tag ...};
   a keyword -> {keyword true}; a map is used as-is. On a symbol the metadata
   rides on the symbol (it stays a bare symbol, so a hint like ^String is
   transparent in params/lets/bodies); other targets use a runtime with-meta. *)

(* --------------------------------------------------------------------------
   Dispatch forms — introduced by "#".
   -------------------------------------------------------------------------- *)

dispatch        = set
                | anon-fn
                | var-quote
                | regex
                | reader-conditional
                | discard            (* #_form — see Whitespace above *)
                | tagged-literal ;

set             = "#{" , { ws | form } , "}" ;     (* a persistent set *)

(* Anonymous function. %, %1.. are positional params; %& is the rest param. *)
anon-fn         = "#(" , { ws | form } , ")" ;     (* -> (fn* [..] body) *)
anon-arg        = "%" | "%" , digit , { digit } | "%&" ;

var-quote       = "#'" , symbol ;                  (* (var symbol) *)

(* Regex literal -> a Janet PEG-backed regex value.
   Supported: groups, greedy/lazy quantifiers, (?:..), lookahead (?=..)/(?!..),
   alternation, anchors ^ $ \b \B, classes, (?i). NOT: lookbehind,
   backreferences, named groups. *)
regex           = '#"' , { ? any char except '"' ? | "\" , ? any char ? } , '"' ;

(* Reader conditional. Jolt reads as the :clj platform; #?@ splices a sequence. *)
reader-conditional
                = "#?@" , "(" , { ws | feature , ws , form } , ")"
                | "#?"  , "(" , { ws | feature , ws , form } , ")" ;
feature         = ":clj" | ":cljs" | ":default" | keyword ;

(* Tagged literal: #tag form. Built-in tags include #inst and #uuid; others
   dispatch to a registered data-reader (else error). *)
tagged-literal  = "#" , symbol , ws , form ;