1 /*
2  * Copyright 2008-2019 Max Kellermann <max.kellermann@gmail.com>
3  *
4  * Redistribution and use in source and binary forms, with or without
5  * modification, are permitted provided that the following conditions
6  * are met:
7  *
8  * - Redistributions of source code must retain the above copyright
9  * notice, this list of conditions and the following disclaimer.
10  *
11  * - Redistributions in binary form must reproduce the above copyright
12  * notice, this list of conditions and the following disclaimer in the
13  * documentation and/or other materials provided with the
14  * distribution.
15  *
16  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
17  * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
18  * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
19  * FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE
20  * FOUNDATION OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
21  * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
22  * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
23  * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
24  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
25  * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
26  * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
27  * OF THE POSSIBILITY OF SUCH DAMAGE.
28  */
29 
30 #include "UriUtil.hxx"
31 #include "ASCII.hxx"
32 #include "SplitString.hxx"
33 
34 #include <array>
35 #include <cassert>
36 #include <cstring>
37 
38 #include <string_view>
39 
40 static const char *
verify_uri_segment(const char * p)41 verify_uri_segment(const char *p) noexcept
42 {
43 	unsigned dots = 0;
44 	while (*p == '.') {
45 		++p;
46 		++dots;
47 	}
48 
49 	if (dots <= 2 && (*p == 0 || *p == '/'))
50 		return nullptr;
51 
52 	const char *q = std::strchr(p + 1, '/');
53 	return q != nullptr ? q : "";
54 }
55 
56 bool
uri_safe_local(const char * uri)57 uri_safe_local(const char *uri) noexcept
58 {
59 	while (true) {
60 		uri = verify_uri_segment(uri);
61 		if (uri == nullptr)
62 			return false;
63 
64 		if (*uri == 0)
65 			return true;
66 
67 		assert(*uri == '/');
68 
69 		++uri;
70 	}
71 }
72 
73 gcc_pure
74 static const char *
SkipUriScheme(const char * uri)75 SkipUriScheme(const char *uri) noexcept
76 {
77 	static constexpr auto schemes = std::array {
78 		"http://", "https://",
79 		"ftp://",
80 		"smb://",
81 	};
82 
83 	for (auto scheme : schemes) {
84 		auto result = StringAfterPrefixCaseASCII(uri, scheme);
85 		if (result != nullptr)
86 			return result;
87 	}
88 
89 	return nullptr;
90 }
91 
92 std::string
uri_remove_auth(const char * uri)93 uri_remove_auth(const char *uri) noexcept
94 {
95 	const char *auth = SkipUriScheme(uri);
96 	if (auth == nullptr)
97 		/* unrecognized URI */
98 		return {};
99 
100 	const char *slash = std::strchr(auth, '/');
101 	if (slash == nullptr)
102 		slash = auth + strlen(auth);
103 
104 	auto at = (const char *)std::memchr(auth, '@', slash - auth);
105 	if (at == nullptr)
106 		/* no auth info present, do nothing */
107 		return {};
108 
109 	/* duplicate the full URI and then delete the auth
110 	   information */
111 	std::string result(uri);
112 	result.erase(auth - uri, at + 1 - auth);
113 	return result;
114 }
115 
116 std::string
uri_squash_dot_segments(const char * uri)117 uri_squash_dot_segments(const char *uri) noexcept
118 {
119 	std::forward_list<std::string_view> path = SplitString(std::string_view(uri), '/');
120 	path.remove_if([](const std::string_view &seg) { return seg == "."; });
121 	path.reverse();
122 
123 	std::string result;
124 
125 	int segskips = 0;
126 	auto it = path.begin();
127 	while (it != path.end()) {
128 		if (*it == "..") {
129 			segskips++;
130 			it++;
131 			continue;
132 		} else if (segskips != 0) {
133 			segskips--;
134 			it++;
135 			continue;
136 		}
137 
138 		result.insert(0, *it);
139 
140 		if (it != path.begin()) {
141 			result.insert(it->length(), "/");
142 		}
143 
144 		it++;
145 	}
146 
147 	return result;
148 }
149