1 (* Copyright (C) 2005, 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/
28 exception Error of int * int * string
30 let regexp number = xml_digit+
32 let regexp ident_decoration = '\'' | '!' | '?' | '`'
33 let regexp ident_cont = xml_letter | xml_digit | '_'
34 let regexp ident = xml_letter ident_cont* ident_decoration*
36 let regexp tex_token = '\\' ident
38 let regexp keyword = '"' ident '"'
40 let regexp implicit = '?'
41 let regexp meta = implicit number
44 ("cic:/" | "theory:/") (* schema *)
45 ident ('/' ident)* (* path *)
46 ('.' ident)+ (* ext *)
47 ("#xpointer(" number ('/' number)+ ")")? (* xpointer *)
49 let error lexbuf msg =
50 let begin_cnum, end_cnum = Ulexing.loc lexbuf in
51 raise (Error (begin_cnum, end_cnum, msg))
52 let error_at_end lexbuf msg =
53 let begin_cnum, end_cnum = Ulexing.loc lexbuf in
54 raise (Error (begin_cnum, end_cnum, msg))
56 let return lexbuf token =
57 let begin_cnum, end_cnum = Ulexing.loc lexbuf in
58 (* TODO handle line/column numbers *)
60 { Lexing.pos_fname = "";
61 Lexing.pos_lnum = -1; Lexing.pos_bol = -1;
62 Lexing.pos_cnum = begin_cnum }
64 let flocation_end = { flocation_begin with Lexing.pos_cnum = end_cnum } in
65 (token, (flocation_begin, flocation_end))
67 let remove_quotes s = String.sub s 1 (String.length s - 2)
71 let lexbuf = Ulexing.from_utf8_stream stream in
72 Token.make_stream_and_flocation
77 | Ulexing.Error -> error_at_end lexbuf "Unexpected character"
78 | Ulexing.InvalidCodepoint p ->
79 error_at_end lexbuf (sprintf "Invalid code point: %d" p))
82 Token.tok_func = tok_func;
83 Token.tok_using = (fun _ -> ());
84 Token.tok_removing = (fun _ -> ());
85 Token.tok_match = Token.default_match;
86 Token.tok_text = Token.lexer_text;
87 Token.tok_comm = None;
90 let expand_macro lexbuf =
92 Ulexing.utf8_sub_lexeme lexbuf 1 (Ulexing.lexeme_length lexbuf - 1)
95 ("SYMBOL", Utf8Macro.expand macro)
96 with Utf8Macro.Macro_not_found _ -> "SYMBOL", Ulexing.utf8_lexeme lexbuf
98 let keyword lexbuf = "KEYWORD", remove_quotes (Ulexing.utf8_lexeme lexbuf)
100 (** {2 Level 1 lexer} *)
102 let rec level1_token = lexer
103 | xml_blank+ -> level1_token lexbuf
104 | ident -> return lexbuf ("IDENT", Ulexing.utf8_lexeme lexbuf)
105 | number -> return lexbuf ("NUMBER", Ulexing.utf8_lexeme lexbuf)
106 | keyword -> return lexbuf (keyword lexbuf)
107 | tex_token -> return lexbuf (expand_macro lexbuf)
108 | eof -> return lexbuf ("EOI", "")
109 | _ -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
111 (** {2 Level 2 lexer} *)
113 let rec level2_token = lexer
114 | xml_blank+ -> level2_token lexbuf
115 | meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf)
116 | implicit -> return lexbuf ("IMPLICIT", Ulexing.utf8_lexeme lexbuf)
117 | ident -> return lexbuf ("IDENT", Ulexing.utf8_lexeme lexbuf)
118 | number -> return lexbuf ("NUMBER", Ulexing.utf8_lexeme lexbuf)
119 | keyword -> return lexbuf (keyword lexbuf)
120 | tex_token -> return lexbuf (expand_macro lexbuf)
121 | uri -> return lexbuf ("URI", Ulexing.utf8_lexeme lexbuf)
122 | eof -> return lexbuf ("EOI", "")
123 | _ -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
125 (* API implementation *)
127 let syntax_pattern_lexer = mk_lexer level1_token
128 let ast_pattern_lexer = mk_lexer level2_token