1 (* Copyright (C) 2004-2005, 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/
26 let gzip_bufsize = 10240
29 start_element: (string -> (string * string) list -> unit) option;
30 end_element: (string -> unit) option;
31 character_data: (string -> unit) option;
32 processing_instruction: (string -> string -> unit) option;
33 comment: (string -> unit) option;
36 let default_callbacks = {
39 character_data = None;
40 processing_instruction = None;
45 [ `Channel of in_channel
47 | `Gzip_channel of Gzip.in_channel
48 | `Gzip_file of string
52 type position = int * int
54 type xml_parser = Expat.expat_parser
56 let create_parser callbacks =
57 let expat_parser = Expat.parser_create ~encoding:None in
58 (match callbacks.start_element with
59 | Some f -> Expat.set_start_element_handler expat_parser f
61 (match callbacks.end_element with
62 | Some f -> Expat.set_end_element_handler expat_parser f
64 (match callbacks.character_data with
65 | Some f -> Expat.set_character_data_handler expat_parser f
67 (match callbacks.processing_instruction with
68 | Some f -> Expat.set_processing_instruction_handler expat_parser f
70 (match callbacks.comment with
71 | Some f -> Expat.set_comment_handler expat_parser f
75 let final = Expat.final
77 let get_position expat_parser =
78 (Expat.get_current_line_number expat_parser,
79 Expat.get_current_column_number expat_parser)
81 let parse expat_parser =
82 let parse_fun = Expat.parse expat_parser in
83 let rec aux = function
86 while true do parse_fun (input_line ic ^ "\n") done
87 with End_of_file -> final expat_parser)
89 let ic = open_in fname in
93 let buf = String.create gzip_bufsize in
96 let bytes = Gzip.input ic buf 0 gzip_bufsize in
97 if bytes = 0 then raise End_of_file;
98 parse_fun (String.sub buf 0 bytes)
100 with End_of_file -> final expat_parser)
101 | `Gzip_file fname ->
102 let ic = Gzip.open_in fname in
103 aux (`Gzip_channel ic);
105 | `String s -> parse_fun s