3 OCaml HTTP - do it yourself (fully OCaml) HTTP daemon
5 Copyright (C) <2002-2004> Stefano Zacchiroli <zack@cs.unibo.it>
7 This program is free software; you can redistribute it and/or modify
8 it under the terms of the GNU General Public License as published by
9 the Free Software Foundation; either version 2 of the License, or
10 (at your option) any later version.
12 This program 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 this program; if not, write to the Free Software
19 Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
29 type url_syntax_option =
30 Url_part_not_recognized
34 * (1) scheme://user:password@host:port/path;params?query#fragment
37 let request_uri_syntax = {
38 url_enable_scheme = Url_part_not_recognized;
39 url_enable_user = Url_part_not_recognized;
40 url_enable_user_param= Url_part_not_recognized;
41 url_enable_password = Url_part_not_recognized;
42 url_enable_host = Url_part_not_recognized;
43 url_enable_port = Url_part_not_recognized;
44 url_enable_path = Url_part_required;
45 url_enable_param = Url_part_not_recognized;
46 url_enable_query = Url_part_allowed;
47 url_enable_fragment = Url_part_not_recognized;
48 url_enable_other = Url_part_not_recognized;
49 url_accepts_8bits = false;
50 url_enable_relative = true;
51 url_is_valid = (fun _ -> true);
55 foo_RE_raw is the uncompiled regexp matching foo
56 foo_RE is the compiled regexp matching foo
57 is_foo is the predicate over string matching foo
60 let separators_RE_raw = "()<>@,;:\\\\\"/\\[\\]?={} \t"
61 let ctls_RE_raw = "\\x00-\\x1F\\x7F"
62 let token_RE_raw = "[^" ^ separators_RE_raw ^ ctls_RE_raw ^ "]+"
63 let lws_RE_raw = "(\r\n)?[ \t]"
64 let quoted_string_RE_raw = "\"(([^\"])|(\\\\\"))*\""
65 let text_RE_raw = "(([^" ^ ctls_RE_raw ^ "])|(" ^ lws_RE_raw ^ "))+"
66 let field_content_RE_raw =
68 "^(((%s)|(%s)|(%s))|(%s))*$"
74 (* following RFC 2616 specifications *)
75 let field_value_RE_raw = "((" ^ field_content_RE_raw ^ ")|(" ^ lws_RE_raw^ "))*"
77 (* smarter implementation: TEXT production is included in the regexp below *)
78 let field_value_RE_raw =
80 "^((%s)|(%s)|(%s)|(%s))*$"
86 let token_RE = Pcre.regexp ("^" ^ token_RE_raw ^ "$")
87 let field_value_RE = Pcre.regexp ("^" ^ field_value_RE_raw ^ "$")
88 let heading_lws_RE = Pcre.regexp (sprintf "^%s*" lws_RE_raw)
89 let trailing_lws_RE = Pcre.regexp (sprintf "%s*$" lws_RE_raw)
91 let is_token s = Pcre.pmatch ~rex:token_RE s
92 let is_field_name = is_token
93 let is_field_value s = Pcre.pmatch ~rex:field_value_RE s
95 let heal_header_name s =
96 if not (is_field_name s) then raise (Invalid_header_name s) else ()
98 let heal_header_value s =
99 if not (is_field_value s) then raise (Invalid_header_value s) else ()
101 let normalize_header_value s =
102 Pcre.replace ~rex:trailing_lws_RE
103 (Pcre.replace ~rex:heading_lws_RE s)
105 let heal_header (name, value) =
106 heal_header_name name;
107 heal_header_value name
109 let url_of_string s =
111 url_of_string request_uri_syntax s
112 with Neturl.Malformed_URL -> raise (Malformed_URL s)
113 let string_of_url = Neturl.string_of_url