more cases for commentary

This commit is contained in:
Mylloon 2023-10-17 15:05:05 +02:00
parent f11c33ff18
commit fadc63e30a
Signed by: Anri
GPG key ID: A82D63DFF8D1317F
2 changed files with 71 additions and 64 deletions

View file

@ -20,82 +20,88 @@ let hexa = "0x" ['0'-'9' 'a'-'f' 'A'-'F']
let bina = "0b" ['0'-'1'] let bina = "0b" ['0'-'1']
let octa = "0o" ['0'-'7'] let octa = "0o" ['0'-'7']
let integers = '-'? (digit+ let printable = [' ' '\t' '\n' '\r' (* 33-126 *)] (* pas sûr *)
| hexa+
| bina+
| octa+)
let printable = [' ' '\t' '\n' '\r' (*33-126*)] (*pas sûr*)
let ident = ['a'-'z']['A'-'Z' 'a'-'z' '0'-'9' '_']*
let constr_id = ['A'-'Z']['A'-'Z' 'a'-'z' '0'-'9' '_']*
let type_variable = ['\'']['a'-'z']['A'-'Z' 'a'-'z' '0'-'9' '_']*
(* On ne peut pas différencier au niveau du lexer var_id label_id et type_con, (* On ne peut pas différencier au niveau du lexer var_id label_id et type_con,
* il faudra le faire à l'analyseur syntaxique *) * il faudra le faire à l'analyseur syntaxique. On fait donc un "ident" pour
* identificateur *)
let ident = ['a'-'z']['A'-'Z' 'a'-'z' '0'-'9' '_']*
let atom = '"' let atom = '"'
let char = ['\'']atom['\'']
let string = ['\"']((atom | '\'' | "\\\""))['\"'] let constr_id = ['A'-'Z']['A'-'Z' 'a'-'z' '0'-'9' '_']*
let type_variable = '`' ['a'-'z']['A'-'Z' 'a'-'z' '0'-'9' '_']*
let int = '-'? (digit+ | hexa+ | bina+ | octa+)
let char = '\'' atom '\''
let string = '\"' ((atom | '\'' | "\\\"")) '\"'
(* let binop = '+' | '-' | '*' | '/' | "&&" | "||"| "=?"| "<=?" |">=?" |"<?" |">?" *) (* let binop = '+' | '-' | '*' | '/' | "&&" | "||"| "=?"| "<=?" |">=?" |"<?" |">?" *)
rule token = parse rule token = parse
(** Layout *) (** Layout *)
| newline { next_line_and token lexbuf } | newline { next_line_and token lexbuf }
| blank+ { token lexbuf } | blank+ { token lexbuf }
| eof { EOF } | eof { EOF }
| "{*" { commentary lexbuf; token lexbuf } | "{*" { commentary lexbuf }
| "##" { commentary_line lexbuf } | "##" { commentary_line lexbuf }
(** Keywords *) (** Keywords *)
| "let" { LET } | "let" { LET }
| "type" { TYPE } | "type" { TYPE }
| "extern" { EXTERN } | "extern" { EXTERN }
| "fun" { FUN } | "fun" { FUN }
| "match" { MATCH } | "match" { MATCH }
| "if" { IF } | "if" { IF }
| "then" { THEN } | "then" { THEN }
| "else" { ELSE } | "else" { ELSE }
| "ref" { REF } | "ref" { REF }
| "while" { WHILE } | "while" { WHILE }
| "do" { DO } | "do" { DO }
| "until" { UNTIL } | "until" { UNTIL }
| "for" { FOR } | "from" { FROM }
| "from" { FROM } | "to" { TO }
| "to" { TO } | "and" { AND }
| "and" { AND } | "for" { FOR }
| "for" { FOR }
(* Fini ? *) (* Fini ? *)
(** Binar operation : pas sûr pour celui là*) (** Binar operation : pas sûr pour celui là *)
(* | binop as b { BINOP (* TODO *) } *) (* | binop as b { BINOP b } *)
(** Operators *) (** Operators *)
(* | '=' { EQUAL } *) (* | '=' { EQUAL } *)
(* ponctuation *) (** Ponctuation *)
| '(' { LPAREN } | '(' { LPAREN }
| ')' { RPAREN } | ')' { RPAREN }
| '[' { LBRACK } | '[' { LBRACK }
| ']' { RBRACK } | ']' { RBRACK }
| '_' { WILDCARD } | '_' { WILDCARD }
| ':' { DPOINT } | ':' { DPOINT }
| "->" { ARROW } | "->" { ARROW }
| "<" { INFERIOR } | "<" { INFERIOR }
| ">" { SUPERIOR } | ">" { SUPERIOR }
(** Values *) (** Values *)
| integers as i { INT (Mint.of_string i) } | int as i { INT (Mint.of_string i) }
| ident as s { ID s } | ident as s { ID s }
| type_variable as s { TID s }
(** Lexing error *) (** Lexing error *)
| _ { error lexbuf "unexpected character." } | _ { error lexbuf "unexpected character." }
and commentary = parse (* TODO: Gérer les imbrications de commentaires *)
| "*}" { () } and commentary = parse
| "{*" { commentary lexbuf; commentary lexbuf } | "*}" { token lexbuf }
| _ { commentary lexbuf } | newline { next_line_and commentary lexbuf }
and commentary_line = parse (** Error *)
| '\n' { next_line_and token lexbuf } | eof { error lexbuf "unclosed commentary." }
| _ { commentary_line lexbuf }
(** Commentary content *)
| _ { commentary lexbuf }
and commentary_line = parse
| newline { next_line_and token lexbuf }
| eof { EOF }
| _ { commentary_line lexbuf }

View file

@ -48,7 +48,7 @@ fundef:
FunctionDefinition(p, e) FunctionDefinition(p, e)
} }
/* ts est temp */ /* ts est temp */
| DPOINT ts=located(type_scheme) i=located(identifier) p=pattern EQUAL e=located(expression) { | DPOINT ts=located(type_scheme) i=located(identifier) p=located(pattern) EQUAL e=located(expression) {
FunctionDefinition(p, e) FunctionDefinition(p, e)
} }
@ -63,18 +63,19 @@ pattern:
ty: ty:
| tc = type_constructor { /* Temporaire None - compile pas */
/* | tc=type_constructor {
TyCon(tc, None) TyCon(tc, None)
} } */
(* Todo version avec l'optionnel*) /* Todo version avec l'optionnel */
| ty1=located(ty) ARROW ty2=located(ty) { | ty1=located(ty) ARROW ty2=located(ty) {
TyArrow(ty1, ty2) TyArrow(ty1, ty2)
} }
| ty1=located(ty) STAR ty2=located(ty) { | ty1=located(ty) STAR ty2=located(ty) {
TyTuple([ty1; ty2]) TyTuple([ty1; ty2])
} }
| ty1=located(ty) STAR ty2=located(ty) STAR liste_ty = separated_list(STAR,located(ty)) { | ty1=located(ty) STAR ty2=located(ty) STAR liste_ty=separated_list(STAR, located(ty)) {
TyTuple(ty1::ty2::liste_ty) TyTuple(ty1::ty2::liste_ty)
} }
| LPAREN type_var=type_variable RPAREN { | LPAREN type_var=type_variable RPAREN {
@ -83,8 +84,8 @@ ty:
type_scheme: type_scheme:
(* il faut peut être modifié le séparateur*) /* il faut peut être modifié le séparateur */
| LBRACK liste_typevar=separated_list(COMMA,located(type_variable)) RBRACK ty=located(ty) { | LBRACK liste_typevar=separated_list(COMMA, located(type_variable)) RBRACK ty=located(ty) {
ForallTy(liste_typevar, ty) ForallTy(liste_typevar, ty)
} }
| ty=located(ty) { | ty=located(ty) {
@ -99,7 +100,7 @@ type_variable:
type_constructor: type_constructor:
| tcon = TID { | tcon=TID {
TCon tcon TCon tcon
} }