X-Git-Url: http://matita.cs.unibo.it/gitweb/?a=blobdiff_plain;f=helm%2Focaml%2Fcic_disambiguation%2FcicTextualLexer2.ml;h=7606344d1b1feea9981fd442e1228084f48ff7b1;hb=12cc5b2b8e7f7bb0b5e315094b008a293a4df6b1;hp=733166d7eeb0dacf27f587db1c136fc57ca2fd61;hpb=bb71ef3952f9dba1487a6b655752438005aa9ec9;p=helm.git diff --git a/helm/ocaml/cic_disambiguation/cicTextualLexer2.ml b/helm/ocaml/cic_disambiguation/cicTextualLexer2.ml index 733166d7e..7606344d1 100644 --- a/helm/ocaml/cic_disambiguation/cicTextualLexer2.ml +++ b/helm/ocaml/cic_disambiguation/cicTextualLexer2.ml @@ -32,41 +32,43 @@ let regexp digit = [ '0' - '9' ] let regexp blank = [ ' ' '\t' '\n' ] let regexp paren = [ '(' '[' '{' ')' ']' '}' ] let regexp implicit = '?' +let regexp placeholder = '%' let regexp symbol_char = [^ 'a' - 'z' 'A' - 'Z' '0' - '9' ' ' '\t' '\n' '\\' '(' '[' '{' ')' ']' '}' '?' ] -let regexp dust = "%%" [^ '\n']* '\n' -let regexp comment_char = [^ ")" ] -let regexp note = "(*" comment_char* "*)" +let regexp comment_char = [^'*'] | '*'[^')'] +let regexp note = "(*" ([^'*'] | "**") comment_char* "*)" -let regexp commentbegin = "(**" -let regexp commentend = "**)" +let regexp commentbegin = "(**" blank +let regexp commentend = "*)" let regexp blanks = blank+ let regexp num = digit+ let regexp tex_token = '\\' alpha+ -let regexp symbol = symbol_char+ +let regexp symbol = symbol_char let regexp ident_cont = alpha | num | '_' | '\'' let regexp ident_cont' = ident_cont | tex_token let regexp ident = (alpha ident_cont*) | ('_' ident_cont+) let regexp ident' = ((alpha | tex_token) ident_cont'*) | ('_' ident_cont'+) +let regexp uri_step = (alpha (ident_cont|'-')*) let regexp meta = implicit num let regexp qstring = '"' [^ '"']* '"' +let regexp uri_suffix = "con"|"ind"|"var" let regexp uri = ("cic:/" | "theory:/") (* schema *) - ident ('/' ident)* (* path *) - ('.' ident)+ (* ext *) - ("#xpointer(" num ('/' num)+ ")")? (* xpointer *) + uri_step ('/' uri_step)* (* path *) + ('.' uri_suffix)+ (* ext *) + ("#xpointer(" num ('/' num)+ ")")? (* xpointer *) (* let regexp catchall = .* *) let keywords = Hashtbl.create 17 let _ = List.iter (fun keyword -> Hashtbl.add keywords keyword ("", keyword)) [ "Prop"; "Type"; "Set"; "let"; "Let"; "rec"; "using"; "match"; "with"; - "in"; "and" ] + "in"; "and"; "to"; "as"; "on"; "names"] let error lexbuf msg = raise (Error (Ulexing.lexeme_start lexbuf, Ulexing.lexeme_end lexbuf, msg)) @@ -127,6 +129,7 @@ let rec token comments = lexer | paren -> return lexbuf ("PAREN", Ulexing.utf8_lexeme lexbuf) | meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf) | implicit -> return lexbuf ("IMPLICIT", Ulexing.utf8_lexeme lexbuf) + | placeholder -> return lexbuf ("PLACEHOLDER", Ulexing.utf8_lexeme lexbuf) | qstring -> return lexbuf ("QSTRING", remove_quotes (Ulexing.utf8_lexeme lexbuf)) | symbol -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf) @@ -138,11 +141,10 @@ let rec token comments = lexer return lexbuf ("SYMBOL", Utf8Macro.expand macro) with Utf8Macro.Macro_not_found _ -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)) - | dust -> token comments lexbuf | note -> (*if comments then*) let comment = - Ulexing.utf8_sub_lexeme lexbuf 2 (Ulexing.lexeme_length lexbuf - 2) + Ulexing.utf8_sub_lexeme lexbuf 2 (Ulexing.lexeme_length lexbuf - 4) in return lexbuf ("NOTE", comment) (*else