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 let regexp alpha = [ 'a' - 'z' 'A' - 'Z' ]
29 let regexp digit = [ '0' - '9' ]
30 let regexp blank = [ ' ' '\t' '\n' ]
32 let regexp blanks = blank+
33 let regexp num = digit+
34 let regexp ident = alpha (alpha | num)*
35 let regexp symbol = [^ 'a' - 'z' 'A' - 'Z' '0' - '9' ' ' '\t' '\n' ]
36 let regexp tex_token = '\\' alpha+
37 let regexp lparen = [ '(' '[' '{' ]
38 let regexp rparen = [ ')' ']' '}' ]
39 let regexp meta = '?' num
41 let keywords = Hashtbl.create 17
43 List.iter (fun keyword -> Hashtbl.add keywords keyword ("", keyword))
44 [ "Prop"; "Type"; "Set"; "let"; "rec"; "using"; "match"; "with" ]
46 let error lexbuf msg =
47 raise (Error (Ulexing.lexeme_start lexbuf, Ulexing.lexeme_end lexbuf, msg))
48 let error_at_end lexbuf msg =
49 raise (Error (Ulexing.lexeme_end lexbuf, Ulexing.lexeme_end lexbuf, msg))
51 let return lexbuf token = (token, Ulexing.loc lexbuf)
54 | blanks -> token lexbuf
56 let lexeme = Ulexing.utf8_lexeme lexbuf in
58 return lexbuf (Hashtbl.find keywords lexeme)
60 return lexbuf ("IDENT", lexeme))
61 | num -> return lexbuf ("INT", Ulexing.utf8_lexeme lexbuf)
62 | lparen -> return lexbuf ("LPAREN", Ulexing.utf8_lexeme lexbuf)
63 | rparen -> return lexbuf ("RPAREN", Ulexing.utf8_lexeme lexbuf)
64 | meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf)
65 | symbol -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
68 Ulexing.utf8_sub_lexeme lexbuf 1 (Ulexing.lexeme_length lexbuf - 1)
71 return lexbuf ("SYMBOL", Macro.expand macro)
72 with Macro.Macro_not_found _ ->
73 return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf))
74 | eof -> return lexbuf ("EOI", "")
75 | _ -> error lexbuf "Invalid character"
78 let lexbuf = Ulexing.from_utf8_stream stream in
79 Token.make_stream_and_location
84 | Ulexing.Error -> error_at_end lexbuf "Unexpected character"
85 | Ulexing.InvalidCodepoint i -> error_at_end lexbuf "Invalid code point")
89 Token.tok_func = tok_func;
90 Token.tok_using = (fun _ -> ());
91 Token.tok_removing = (fun _ -> ());
92 Token.tok_match = Token.default_match;
93 Token.tok_text = Token.lexer_text;
94 Token.tok_comm = None;