From fadc63e30a199524fab99c4c237cff00e7f4d3fd Mon Sep 17 00:00:00 2001 From: Mylloon Date: Tue, 17 Oct 2023 15:05:05 +0200 Subject: [PATCH] more cases for commentary --- flap/src/hopix/hopixLexer.mll | 118 +++++++++++++++++---------------- flap/src/hopix/hopixParser.mly | 17 ++--- 2 files changed, 71 insertions(+), 64 deletions(-) diff --git a/flap/src/hopix/hopixLexer.mll b/flap/src/hopix/hopixLexer.mll index f8a4112..59d6481 100644 --- a/flap/src/hopix/hopixLexer.mll +++ b/flap/src/hopix/hopixLexer.mll @@ -20,82 +20,88 @@ let hexa = "0x" ['0'-'9' 'a'-'f' 'A'-'F'] let bina = "0b" ['0'-'1'] let octa = "0o" ['0'-'7'] -let integers = '-'? (digit+ - | hexa+ - | bina+ - | octa+) +let printable = [' ' '\t' '\n' '\r' (* 33-126 *)] (* pas sûr *) -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, - * 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 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 = '+' | '-' | '*' | '/' | "&&" | "||"| "=?"| "<=?" |">=?" |"?" *) rule token = parse (** Layout *) - | newline { next_line_and token lexbuf } - | blank+ { token lexbuf } - | eof { EOF } - | "{*" { commentary lexbuf; token lexbuf } - | "##" { commentary_line lexbuf } + | newline { next_line_and token lexbuf } + | blank+ { token lexbuf } + | eof { EOF } + | "{*" { commentary lexbuf } + | "##" { commentary_line lexbuf } (** Keywords *) - | "let" { LET } - | "type" { TYPE } - | "extern" { EXTERN } - | "fun" { FUN } - | "match" { MATCH } - | "if" { IF } - | "then" { THEN } - | "else" { ELSE } - | "ref" { REF } - | "while" { WHILE } - | "do" { DO } - | "until" { UNTIL } - | "for" { FOR } - | "from" { FROM } - | "to" { TO } - | "and" { AND } - | "for" { FOR } + | "let" { LET } + | "type" { TYPE } + | "extern" { EXTERN } + | "fun" { FUN } + | "match" { MATCH } + | "if" { IF } + | "then" { THEN } + | "else" { ELSE } + | "ref" { REF } + | "while" { WHILE } + | "do" { DO } + | "until" { UNTIL } + | "from" { FROM } + | "to" { TO } + | "and" { AND } + | "for" { FOR } (* Fini ? *) - (** Binar operation : pas sûr pour celui là*) - (* | binop as b { BINOP (* TODO *) } *) + (** Binar operation : pas sûr pour celui là *) + (* | binop as b { BINOP b } *) (** Operators *) - (* | '=' { EQUAL } *) + (* | '=' { EQUAL } *) - (* ponctuation *) - | '(' { LPAREN } - | ')' { RPAREN } - | '[' { LBRACK } - | ']' { RBRACK } - | '_' { WILDCARD } - | ':' { DPOINT } - | "->" { ARROW } - | "<" { INFERIOR } - | ">" { SUPERIOR } + (** Ponctuation *) + | '(' { LPAREN } + | ')' { RPAREN } + | '[' { LBRACK } + | ']' { RBRACK } + | '_' { WILDCARD } + | ':' { DPOINT } + | "->" { ARROW } + | "<" { INFERIOR } + | ">" { SUPERIOR } (** Values *) - | integers as i { INT (Mint.of_string i) } - | ident as s { ID s } + | int as i { INT (Mint.of_string i) } + | ident as s { ID s } + | type_variable as s { TID s } (** Lexing error *) - | _ { error lexbuf "unexpected character." } + | _ { error lexbuf "unexpected character." } - and commentary = parse - | "*}" { () } - | "{*" { commentary lexbuf; commentary lexbuf } - | _ { commentary lexbuf } +(* TODO: Gérer les imbrications de commentaires *) +and commentary = parse + | "*}" { token lexbuf } + | newline { next_line_and commentary lexbuf } - and commentary_line = parse - | '\n' { next_line_and token lexbuf } - | _ { commentary_line lexbuf } + (** Error *) + | eof { error lexbuf "unclosed commentary." } + + (** Commentary content *) + | _ { commentary lexbuf } + +and commentary_line = parse + | newline { next_line_and token lexbuf } + | eof { EOF } + | _ { commentary_line lexbuf } diff --git a/flap/src/hopix/hopixParser.mly b/flap/src/hopix/hopixParser.mly index 666b13e..7f762be 100644 --- a/flap/src/hopix/hopixParser.mly +++ b/flap/src/hopix/hopixParser.mly @@ -48,7 +48,7 @@ fundef: FunctionDefinition(p, e) } /* 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) } @@ -63,18 +63,19 @@ pattern: ty: -| tc = type_constructor { +/* Temporaire None - compile pas */ +/* | tc=type_constructor { TyCon(tc, None) - } + } */ -(* Todo version avec l'optionnel*) +/* Todo version avec l'optionnel */ | ty1=located(ty) ARROW ty2=located(ty) { TyArrow(ty1, ty2) } | ty1=located(ty) STAR ty2=located(ty) { 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) } | LPAREN type_var=type_variable RPAREN { @@ -83,8 +84,8 @@ ty: type_scheme: -(* il faut peut être modifié le séparateur*) -| LBRACK liste_typevar=separated_list(COMMA,located(type_variable)) RBRACK ty=located(ty) { +/* il faut peut être modifié le séparateur */ +| LBRACK liste_typevar=separated_list(COMMA, located(type_variable)) RBRACK ty=located(ty) { ForallTy(liste_typevar, ty) } | ty=located(ty) { @@ -99,7 +100,7 @@ type_variable: type_constructor: -| tcon = TID { +| tcon=TID { TCon tcon }