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 delim_begin = "\\["
39 let regexp delim_end = "\\]"
41 let regexp keyword = '"' ident '"'
42 let regexp qkeyword = "'" ident "'"
44 let regexp implicit = '?'
45 let regexp meta = implicit number
47 let regexp csymbol = '\'' ident
49 let regexp begin_group = "@{" | "${"
50 let regexp end_group = '}'
51 let regexp wildcard = "$_"
52 let regexp ast_ident = "@" ident
53 let regexp ast_csymbol = "@" csymbol
54 let regexp meta_ident = "$" ident
55 let regexp meta_anonymous = "$_"
56 let regexp qstring = '"' [^ '"']* '"'
61 "over"; "atop"; "frac";
66 [ "hbox"; "hvbox"; "hovbox"; "vbox";
68 "list0"; "list1"; "sep";
70 "term"; "ident"; "number"
73 let level2_meta_keywords =
74 [ "if"; "then"; "else";
75 "fold"; "left"; "right"; "rec";
78 "anonymous"; "ident"; "number"; "term"; "fresh"
81 (* (string, unit) Hashtbl.t, to exploit multiple bindings *)
82 let level2_ast_keywords = Hashtbl.create 23
84 (* TODO ZACK: keyword list almost cut and paste from cicTextualLexer2.ml, to
86 List.iter (fun k -> Hashtbl.add level2_ast_keywords k ())
87 [ "Prop"; "Type"; "Set"; "let"; "rec"; "corec"; "match"; "with"; "in";
90 let add_level2_ast_keyword k = Hashtbl.add level2_ast_keywords k ()
91 let remove_level2_ast_keyword k = Hashtbl.remove level2_ast_keywords k
94 ("cic:/" | "theory:/") (* schema *)
95 ident ('/' ident)* (* path *)
96 ('.' ident)+ (* ext *)
97 ("#xpointer(" number ('/' number)+ ")")? (* xpointer *)
99 let error lexbuf msg =
100 let begin_cnum, end_cnum = Ulexing.loc lexbuf in
101 raise (Error (begin_cnum, end_cnum, msg))
102 let error_at_end lexbuf msg =
103 let begin_cnum, end_cnum = Ulexing.loc lexbuf in
104 raise (Error (begin_cnum, end_cnum, msg))
106 let return_with_loc token begin_cnum end_cnum =
107 (* TODO handle line/column numbers *)
108 let flocation_begin =
109 { Lexing.pos_fname = "";
110 Lexing.pos_lnum = -1; Lexing.pos_bol = -1;
111 Lexing.pos_cnum = begin_cnum }
113 let flocation_end = { flocation_begin with Lexing.pos_cnum = end_cnum } in
114 (token, (flocation_begin, flocation_end))
116 let return lexbuf token =
117 let begin_cnum, end_cnum = Ulexing.loc lexbuf in
118 return_with_loc token begin_cnum end_cnum
120 let return_lexeme lexbuf name = return lexbuf (name, Ulexing.utf8_lexeme lexbuf)
122 let remove_quotes s = String.sub s 1 (String.length s - 2)
125 let tok_func stream =
126 let lexbuf = Ulexing.from_utf8_stream stream in
127 Token.make_stream_and_flocation
132 | Ulexing.Error -> error_at_end lexbuf "Unexpected character"
133 | Ulexing.InvalidCodepoint p ->
134 error_at_end lexbuf (sprintf "Invalid code point: %d" p))
137 Token.tok_func = tok_func;
138 Token.tok_using = (fun _ -> ());
139 Token.tok_removing = (fun _ -> ());
140 Token.tok_match = Token.default_match;
141 Token.tok_text = Token.lexer_text;
142 Token.tok_comm = None;
145 let expand_macro lexbuf =
147 Ulexing.utf8_sub_lexeme lexbuf 1 (Ulexing.lexeme_length lexbuf - 1)
150 ("SYMBOL", Utf8Macro.expand macro)
151 with Utf8Macro.Macro_not_found _ -> "SYMBOL", Ulexing.utf8_lexeme lexbuf
153 let keyword lexbuf = "KEYWORD", remove_quotes (Ulexing.utf8_lexeme lexbuf)
155 let remove_quotes s = String.sub s 1 (String.length s - 2)
156 let remove_left_quote s = String.sub s 1 (String.length s - 1)
158 let rec level2_pattern_token_group counter buffer = lexer
160 if (counter > 0) then
161 Buffer.add_string buffer (Ulexing.utf8_lexeme lexbuf) ;
162 snd (Ulexing.loc lexbuf)
164 Buffer.add_string buffer (Ulexing.utf8_lexeme lexbuf) ;
165 ignore (level2_pattern_token_group (counter + 1) buffer lexbuf) ;
166 level2_pattern_token_group counter buffer lexbuf
168 Buffer.add_string buffer (Ulexing.utf8_lexeme lexbuf) ;
169 level2_pattern_token_group counter buffer lexbuf
171 let read_unparsed_group token_name lexbuf =
172 let buffer = Buffer.create 16 in
173 let begin_cnum, _ = Ulexing.loc lexbuf in
174 let end_cnum = level2_pattern_token_group 0 buffer lexbuf in
175 return_with_loc (token_name, Buffer.contents buffer) begin_cnum end_cnum
177 let rec level2_meta_token = lexer
178 | xml_blank+ -> level2_meta_token lexbuf
180 let s = Ulexing.utf8_lexeme lexbuf in
182 if List.mem s level2_meta_keywords then
183 return lexbuf ("", s)
185 return lexbuf ("IDENT", s)
187 | "@{" -> read_unparsed_group "UNPARSED_AST" lexbuf
189 return lexbuf ("UNPARSED_AST",
190 remove_left_quote (Ulexing.utf8_lexeme lexbuf))
192 return lexbuf ("UNPARSED_AST",
193 remove_left_quote (Ulexing.utf8_lexeme lexbuf))
194 | eof -> return lexbuf ("EOI", "")
196 let rec level2_ast_token = lexer
197 | xml_blank+ -> level2_ast_token lexbuf
198 | meta -> return lexbuf ("META", Ulexing.utf8_lexeme lexbuf)
199 | implicit -> return lexbuf ("IMPLICIT", Ulexing.utf8_lexeme lexbuf)
201 let lexeme = Ulexing.utf8_lexeme lexbuf in
202 if Hashtbl.mem level2_ast_keywords lexeme then
203 return lexbuf ("", lexeme)
205 return lexbuf ("IDENT", lexeme)
206 | number -> return lexbuf ("NUMBER", Ulexing.utf8_lexeme lexbuf)
207 | keyword -> return lexbuf (keyword lexbuf)
208 | tex_token -> return lexbuf (expand_macro lexbuf)
209 | uri -> return lexbuf ("URI", Ulexing.utf8_lexeme lexbuf)
211 return lexbuf ("QSTRING", remove_quotes (Ulexing.utf8_lexeme lexbuf))
212 | csymbol -> return lexbuf ("CSYMBOL", Ulexing.utf8_lexeme lexbuf)
213 | "${" -> read_unparsed_group "UNPARSED_META" lexbuf
214 | "@{" -> read_unparsed_group "UNPARSED_AST" lexbuf
215 | '(' -> return lexbuf ("LPAREN", "")
216 | ')' -> return lexbuf ("RPAREN", "")
218 return lexbuf ("UNPARSED_META",
219 remove_left_quote (Ulexing.utf8_lexeme lexbuf))
220 | meta_anonymous -> return lexbuf ("UNPARSED_META", "anonymous")
221 | _ -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
222 | eof -> return lexbuf ("EOI", "")
224 let rec level1_pattern_token = lexer
225 | xml_blank+ -> level1_pattern_token lexbuf
226 | number -> return lexbuf ("NUMBER", Ulexing.utf8_lexeme lexbuf)
228 let s = Ulexing.utf8_lexeme lexbuf in
230 if List.mem s level1_keywords then
231 return lexbuf ("", s)
233 return lexbuf ("IDENT", s)
235 | tex_token -> return lexbuf (expand_macro lexbuf)
237 return lexbuf ("QKEYWORD", remove_quotes (Ulexing.utf8_lexeme lexbuf))
238 | '(' -> return lexbuf ("LPAREN", "")
239 | ')' -> return lexbuf ("RPAREN", "")
240 | eof -> return lexbuf ("EOI", "")
241 | _ -> return lexbuf ("SYMBOL", Ulexing.utf8_lexeme lexbuf)
243 (* API implementation *)
245 let level1_pattern_lexer = mk_lexer level1_pattern_token
246 let level2_ast_lexer = mk_lexer level2_ast_token
247 let level2_meta_lexer = mk_lexer level2_meta_token