1 // src/URI.cc
2 // This file is part of libpbe; see http://anyterm.org/
3 // (C) 2005-2008 Philip Endecott
4
5 // This program is free software; you can redistribute it and/or modify
6 // it under the terms of the GNU General Public License as published by
7 // the Free Software Foundation; either version 2 of the License, or
8 // any later version.
9 //
10 // This program is distributed in the hope that it will be useful,
11 // but WITHOUT ANY WARRANTY; without even the implied warranty of
12 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 // GNU General Public License for more details.
14 //
15 // You should have received a copy of the GNU General Public License
16 // along with this program; if not, write to the Free Software
17 // Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
18
19 #include "URI.hh"
20
21 #include <boost/spirit/include/classic.hpp>
22 #include <boost/spirit/home/classic/actor/insert_at_actor.hpp>
23 #include <boost/spirit/home/classic/dynamic/if.hpp>
24 #include <boost/spirit/home/classic/utility/loops.hpp>
25 #include <boost/spirit/home/classic/iterator/multi_pass.hpp>
26
27 #include <boost/lexical_cast.hpp>
28 #include <boost/scoped_array.hpp>
29
30 #include <map>
31
32 using namespace std;
33 using namespace boost::spirit::classic;
34
35
36 namespace pbe {
37
38
URI(string absolute_uri)39 URI::URI(string absolute_uri):
40 port(0)
41 {
42 typedef rule<> rule_t;
43
44 // URI parsing EBNF based on
45 // RFC2616
46 // RFC2396
47 // HTTP/1.1 Errata (http://skrb.org/ietf/http_errata.html)
48
49 rule_t mark = ch_p('-') | '_' | '.' | '!' | '~' | '*' | '\'' | '(' | ')';
50
51 rule_t unreserved = alnum_p | mark;
52
53 rule_t escaped = ch_p('%') >> xdigit_p >> xdigit_p;
54
55 rule_t reserved = ch_p(';') | '/' | '?' | ':' | '@' | '&' | '=' | '+' | '$' | ',';
56
57 rule_t pchar = unreserved | escaped | ':' | '@' | '&' | '=' | '+' | '$' | ',';
58
59 rule_t param = *pchar;
60
61 rule_t segment = *pchar >> *(';' >> param);
62
63 rule_t path_segments = segment >> *('/' >> segment);
64
65 rule_t abs_path = ( ch_p('/') >> path_segments )[assign_a(URI::abs_path)];
66
67 rule_t scheme = alpha_p >> *(alpha_p | digit_p | '+' | '-' | '.' );
68
69 rule_t userinfo = *(unreserved | escaped | ';' | ':' | '&' | '=' | '+' | '$' | ',' );
70
71 //rule_t domainlabel = alnum_p | alnum_p >> *(alnum_p | '-') >> alnum_p;
72 rule_t domainlabel = *(alnum_p | '-');
73
74 //rule_t toplabel = alpha_p | alpha_p >> *(alnum_p | '-') >> alnum_p;
75
76 //rule_t hostname = *(domainlabel >> '.') >> toplabel >> !ch_p('.');
77 rule_t hostname = domainlabel % ch_p('.');
78
79 uint_parser<unsigned,10,1,3> decimal_byte;
80
81 rule_t ipv4address = decimal_byte >> '.' >> decimal_byte >> '.' >>
82 decimal_byte >> '.' >> decimal_byte;
83
84 rule_t host = hostname | ipv4address;
85
86 rule_t port = uint_p[assign_a(URI::port)];
87
88 rule_t hostport = host[assign_a(URI::host)]
89 >> !(':' >> port);
90
91 rule_t server = !( !(userinfo[assign_a(URI::userinfo)] >> '@') >> hostport );
92
93 rule_t reg_name = +(unreserved | escaped | '$' | ',' | ';' | ':' | '@' |
94 '&' | '=' | '+');
95
96 rule_t authority = server | reg_name;
97
98 rule_t net_path = str_p("//") >> authority >> !abs_path;
99
100 rule_t uric = reserved | unreserved | escaped;
101
102 rule_t query = (*uric) [assign_a(URI::query)];
103
104 rule_t hier_part = (net_path | abs_path) >> !('?' >> query);
105
106 rule_t uric_no_slash = unreserved | escaped | ';' | '?' | ':' | '@' |
107 '&' | '=' | '+' | '$' | ',';
108
109 rule_t opaque_part = uric_no_slash >> *uric;
110
111 rule_t absoluteURI = scheme[assign_a(URI::scheme)] >> ':' >> (hier_part | opaque_part);
112
113 if (!parse(absolute_uri.c_str(), absoluteURI).full) {
114 throw SyntaxError();
115 }
116 }
117
118
119 };
120
121