1 (* Copyright (C) 2004, HELM Team.
3 * This file is part of HELM, an Hypertextual, Electronic
4 * Library of Mathematics, developed at the Computer Science
5 * Department, University of Bologna, Italy.
7 * HELM is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation; either version 2
10 * of the License, or (at your option) any later version.
12 * HELM is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 * GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with HELM; if not, write to the Free Software
19 * Foundation, Inc., 59 Temple Place - Suite 330, Boston,
22 * For details, see the HELM World-Wide-Web page,
23 * http://helm.cs.unibo.it/
26 exception Error of int * int * string
28 exception Not_an_extended_ident
30 let regexp alpha = [ 'a' - 'z' 'A' - 'Z' ]
31 let regexp digit = [ '0' - '9' ]
32 let regexp blank = [ ' ' '\t' '\n' ]
34 let regexp blanks = blank+
35 let regexp num = digit+
36 let regexp tex_token = '\\' alpha+
37 let regexp symbol = [^ 'a' - 'z' 'A' - 'Z' '0' - '9' ' ' '\t' '\n' ]
38 let regexp ident_cont = alpha | num | '_' | '\''
39 let regexp ident_cont' = ident_cont | tex_token
40 let regexp ident = (alpha ident_cont*) | ('_' ident_cont+)
41 let regexp ident' = ((alpha | tex_token) ident_cont'*) | ('_' ident_cont'+)
42 let regexp paren = [ '(' '[' '{' ')' ']' '}' ]
43 let regexp implicit = '?'
44 let regexp meta = '?' num
45 let regexp qstring = '"' [^ '"']* '"'
47 (* schema *) (* path *) (* ext *) (* xpointer *)
48 ("cic:/" | "theory:/") ident ('/' ident)* ('.' ident)+ ('#' num ('/' num)*)?
49 (* let regexp catchall = .* *)
51 let keywords = Hashtbl.create 17
53 List.iter (fun keyword -> Hashtbl.add keywords keyword ("", keyword))
54 [ "Prop"; "Type"; "Set"; "let"; "rec"; "using"; "match"; "with" ]
56 let error lexbuf msg =
57 raise (Error (Ulexing.lexeme_start lexbuf, Ulexing.lexeme_end lexbuf, msg))
58 let error_at_end lexbuf msg =
59 raise (Error (Ulexing.lexeme_end lexbuf, Ulexing.lexeme_end lexbuf, msg))
61 let return lexbuf token = (token, Ulexing.loc lexbuf)
64 let parse_ext_ident ident =
65 let len = String.length ident in
66 let buf = Buffer.create len in
67 let in_tex_token = ref false in
68 let tex_token = Buffer.create 10 in
70 for i = 0 to len - 1 do
72 | '\' when not !in_tex_token ->
76 with Invalid_argument -> assert false
78 let rec token' = lexer
81 let ident = parse_ext_ident (Ulexing.utf8_lexeme lexbuf) in
82 return lexbuf ("IDENT'", ident)
83 with Not_an_extended_ident ->
84 Ulexing.rollback lexbuf;
87 Ulexing.rollback lexbuf;
93 | blanks -> token lexbuf
94 | uri -> return lexbuf ("URI", Ulexing.utf8_lexeme lexbuf)
96 let lexeme = Ulexing.utf8_lexeme lexbuf in
98 return lexbuf (Hashtbl.find keywords lexeme)
99 with Not_found -> return lexbuf ("IDENT", lexeme))
100 | num -> return lexbuf ("NUM", Ulexing.utf8_lexeme lexbuf)
101 | paren -> return lexbuf ("PAREN", Ulexing.utf8_lexeme lexbuf)
102 | meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf)
103 | implicit -> return lexbuf ("IMPLICIT", Ulexing.utf8_lexeme lexbuf)
105 let lexeme = Ulexing.utf8_lexeme lexbuf in
106 let s = String.sub lexeme 1 (String.length lexeme - 2) in
107 return lexbuf ("QSTRING", s)
108 | symbol -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
111 Ulexing.utf8_sub_lexeme lexbuf 1 (Ulexing.lexeme_length lexbuf - 1)
114 return lexbuf ("SYMBOL", CicTextualParser2Macro.expand macro)
115 with CicTextualParser2Macro.Macro_not_found _ ->
116 return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf))
117 | eof -> return lexbuf ("EOI", "")
118 | _ -> error lexbuf "Invalid character"
120 let tok_func stream =
121 let lexbuf = Ulexing.from_utf8_stream stream in
122 Token.make_stream_and_location
127 | Ulexing.Error -> error_at_end lexbuf "Unexpected character"
128 | Ulexing.InvalidCodepoint i -> error_at_end lexbuf "Invalid code point")
132 Token.tok_func = tok_func;
133 Token.tok_using = (fun _ -> ());
134 Token.tok_removing = (fun _ -> ());
135 Token.tok_match = Token.default_match;
136 Token.tok_text = Token.lexer_text;
137 Token.tok_comm = None;