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' ]
33 let regexp paren = [ '(' '[' '{' ')' ']' '}' ]
34 let regexp implicit = '?'
35 let regexp placeholder = '%'
36 let regexp symbol_char =
37 [^ 'a' - 'z' 'A' - 'Z' '0' - '9'
39 '\\' '(' '[' '{' ')' ']' '}' '?'
42 let regexp comment_char = [^'*'] | '*'[^')']
43 let regexp note = "(*" ([^'*'] | "**") comment_char* "*)"
45 let regexp commentbegin = "(**" blank
46 let regexp commentend = "*)"
48 let regexp blanks = blank+
49 let regexp num = digit+
50 let regexp tex_token = '\\' alpha+
51 let regexp symbol = symbol_char
52 let regexp ident_cont = alpha | num | '_' | '\''
53 let regexp ident_cont' = ident_cont | tex_token
54 let regexp ident = (alpha ident_cont*) | ('_' ident_cont+)
55 let regexp ident' = ((alpha | tex_token) ident_cont'*) | ('_' ident_cont'+)
56 let regexp meta = implicit num
57 let regexp qstring = '"' [^ '"']* '"'
59 ("cic:/" | "theory:/") (* schema *)
60 ident ('/' ident)* (* path *)
61 ('.' ident)+ (* ext *)
62 ("#xpointer(" num ('/' num)+ ")")? (* xpointer *)
63 (* let regexp catchall = .* *)
65 let keywords = Hashtbl.create 17
67 List.iter (fun keyword -> Hashtbl.add keywords keyword ("", keyword))
68 [ "Prop"; "Type"; "Set"; "let"; "Let"; "rec"; "using"; "match"; "with";
69 "in"; "and"; "to"; "as"; "on"]
71 let error lexbuf msg =
72 raise (Error (Ulexing.lexeme_start lexbuf, Ulexing.lexeme_end lexbuf, msg))
73 let error_at_end lexbuf msg =
74 raise (Error (Ulexing.lexeme_end lexbuf, Ulexing.lexeme_end lexbuf, msg))
76 let return lexbuf token =
78 { Lexing.pos_fname = ""; Lexing.pos_lnum = -1; Lexing.pos_bol = -1;
79 Lexing.pos_cnum = Ulexing.lexeme_start lexbuf }
82 { flocation_begin with Lexing.pos_cnum = Ulexing.lexeme_end lexbuf }
84 (token, (flocation_begin, flocation_end))
87 let parse_ext_ident ident =
88 let len = String.length ident in
89 let buf = Buffer.create len in
90 let in_tex_token = ref false in
91 let tex_token = Buffer.create 10 in
93 for i = 0 to len - 1 do
95 | '\' when not !in_tex_token ->
99 with Invalid_argument -> assert false
101 let rec token' = lexer
104 let ident = parse_ext_ident (Ulexing.utf8_lexeme lexbuf) in
105 return lexbuf ("IDENT'", ident)
106 with Not_an_extended_ident ->
107 Ulexing.rollback lexbuf;
110 Ulexing.rollback lexbuf;
116 let remove_quotes s = String.sub s 1 (String.length s - 2)
118 let rec token comments = lexer
119 | blanks -> token comments lexbuf
120 | uri -> return lexbuf ("URI", Ulexing.utf8_lexeme lexbuf)
122 let lexeme = Ulexing.utf8_lexeme lexbuf in
124 return lexbuf (Hashtbl.find keywords lexeme)
125 with Not_found -> return lexbuf ("IDENT", lexeme))
126 | num -> return lexbuf ("NUM", Ulexing.utf8_lexeme lexbuf)
127 | paren -> return lexbuf ("PAREN", Ulexing.utf8_lexeme lexbuf)
128 | meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf)
129 | implicit -> return lexbuf ("IMPLICIT", Ulexing.utf8_lexeme lexbuf)
130 | placeholder -> return lexbuf ("PLACEHOLDER", Ulexing.utf8_lexeme lexbuf)
132 return lexbuf ("QSTRING", remove_quotes (Ulexing.utf8_lexeme lexbuf))
133 | symbol -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
136 Ulexing.utf8_sub_lexeme lexbuf 1 (Ulexing.lexeme_length lexbuf - 1)
139 return lexbuf ("SYMBOL", Utf8Macro.expand macro)
140 with Utf8Macro.Macro_not_found _ ->
141 return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf))
145 Ulexing.utf8_sub_lexeme lexbuf 2 (Ulexing.lexeme_length lexbuf - 4)
147 return lexbuf ("NOTE", comment)
149 token comments lexbuf*)
150 | commentbegin -> return lexbuf ("BEGINCOMMENT","")
151 | commentend -> return lexbuf ("ENDCOMMENT","")
152 | eof -> return lexbuf ("EOI", "")
153 | _ -> error lexbuf "Invalid character"
155 let tok_func comments stream =
156 let lexbuf = Ulexing.from_utf8_stream stream in
157 Token.make_stream_and_flocation
160 token comments lexbuf
162 | Ulexing.Error -> error_at_end lexbuf "Unexpected character"
163 | Ulexing.InvalidCodepoint i -> error_at_end lexbuf "Invalid code point")
165 let cic_lexer ?(comments = false) () =
167 Token.tok_func = tok_func comments;
168 Token.tok_using = (fun _ -> ());
169 Token.tok_removing = (fun _ -> ());
170 Token.tok_match = Token.default_match;
171 Token.tok_text = Token.lexer_text;
172 Token.tok_comm = None;