1 /*
2 * Copyright (C) 2008 Apple Inc. All Rights Reserved.
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 * 1. Redistributions of source code must retain the above copyright
8 * notice, this list of conditions and the following disclaimer.
9 * 2. Redistributions in binary form must reproduce the above copyright
10 * notice, this list of conditions and the following disclaimer in the
11 * documentation and/or other materials provided with the distribution.
12 *
13 * THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
14 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
15 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
16 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR
17 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
18 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
19 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
20 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
21 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
22 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
23 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
24 */
25
26 #include "config.h"
27 #include "ManifestParser.h"
28
29 #if ENABLE(OFFLINE_WEB_APPLICATIONS)
30
31 #include "KURL.h"
32 #include "TextResourceDecoder.h"
33 #include <wtf/unicode/CharacterNames.h>
34
35 using namespace std;
36
37 namespace WebCore {
38
39 enum Mode { Explicit, Fallback, OnlineWhitelist, Unknown };
40
parseManifest(const KURL & manifestURL,const char * data,int length,Manifest & manifest)41 bool parseManifest(const KURL& manifestURL, const char* data, int length, Manifest& manifest)
42 {
43 ASSERT(manifest.explicitURLs.isEmpty());
44 ASSERT(manifest.onlineWhitelistedURLs.isEmpty());
45 ASSERT(manifest.fallbackURLs.isEmpty());
46 manifest.allowAllNetworkRequests = false;
47
48 Mode mode = Explicit;
49
50 RefPtr<TextResourceDecoder> decoder = TextResourceDecoder::create("text/cache-manifest", "UTF-8");
51 String s = decoder->decode(data, length);
52 s += decoder->flush();
53
54 // Look for the magic signature: "^\xFEFF?CACHE MANIFEST[ \t]?" (the BOM is removed by TextResourceDecoder).
55 // Example: "CACHE MANIFEST #comment" is a valid signature.
56 // Example: "CACHE MANIFEST;V2" is not.
57 if (!s.startsWith("CACHE MANIFEST"))
58 return false;
59
60 const UChar* end = s.characters() + s.length();
61 const UChar* p = s.characters() + 14; // "CACHE MANIFEST" is 14 characters.
62
63 if (p < end && *p != ' ' && *p != '\t' && *p != '\n' && *p != '\r')
64 return false;
65
66 // Skip to the end of the line.
67 while (p < end && *p != '\r' && *p != '\n')
68 p++;
69
70 while (1) {
71 // Skip whitespace
72 while (p < end && (*p == '\n' || *p == '\r' || *p == ' ' || *p == '\t'))
73 p++;
74
75 if (p == end)
76 break;
77
78 const UChar* lineStart = p;
79
80 // Find the end of the line
81 while (p < end && *p != '\r' && *p != '\n')
82 p++;
83
84 // Check if we have a comment
85 if (*lineStart == '#')
86 continue;
87
88 // Get rid of trailing whitespace
89 const UChar* tmp = p - 1;
90 while (tmp > lineStart && (*tmp == ' ' || *tmp == '\t'))
91 tmp--;
92
93 String line(lineStart, tmp - lineStart + 1);
94
95 if (line == "CACHE:")
96 mode = Explicit;
97 else if (line == "FALLBACK:")
98 mode = Fallback;
99 else if (line == "NETWORK:")
100 mode = OnlineWhitelist;
101 else if (line.endsWith(":"))
102 mode = Unknown;
103 else if (mode == Unknown)
104 continue;
105 else if (mode == Explicit || mode == OnlineWhitelist) {
106 const UChar* p = line.characters();
107 const UChar* lineEnd = p + line.length();
108
109 // Look for whitespace separating the URL from subsequent ignored tokens.
110 while (p < lineEnd && *p != '\t' && *p != ' ')
111 p++;
112
113 if (mode == OnlineWhitelist && p - line.characters() == 1 && *line.characters() == '*') {
114 // Wildcard was found.
115 manifest.allowAllNetworkRequests = true;
116 continue;
117 }
118
119 KURL url(manifestURL, String(line.characters(), p - line.characters()));
120
121 if (!url.isValid())
122 continue;
123
124 if (url.hasFragmentIdentifier())
125 url.removeFragmentIdentifier();
126
127 if (!equalIgnoringCase(url.protocol(), manifestURL.protocol()))
128 continue;
129
130 if (mode == Explicit && manifestURL.protocolIs("https") && !protocolHostAndPortAreEqual(manifestURL, url))
131 continue;
132
133 if (mode == Explicit)
134 manifest.explicitURLs.add(url.string());
135 else
136 manifest.onlineWhitelistedURLs.append(url);
137
138 } else if (mode == Fallback) {
139 const UChar* p = line.characters();
140 const UChar* lineEnd = p + line.length();
141
142 // Look for whitespace separating the two URLs
143 while (p < lineEnd && *p != '\t' && *p != ' ')
144 p++;
145
146 if (p == lineEnd) {
147 // There was no whitespace separating the URLs.
148 continue;
149 }
150
151 KURL namespaceURL(manifestURL, String(line.characters(), p - line.characters()));
152 if (!namespaceURL.isValid())
153 continue;
154 if (namespaceURL.hasFragmentIdentifier())
155 namespaceURL.removeFragmentIdentifier();
156
157 if (!protocolHostAndPortAreEqual(manifestURL, namespaceURL))
158 continue;
159
160 // Skip whitespace separating fallback namespace from URL.
161 while (p < lineEnd && (*p == '\t' || *p == ' '))
162 p++;
163
164 // Look for whitespace separating the URL from subsequent ignored tokens.
165 const UChar* fallbackStart = p;
166 while (p < lineEnd && *p != '\t' && *p != ' ')
167 p++;
168
169 KURL fallbackURL(manifestURL, String(fallbackStart, p - fallbackStart));
170 if (!fallbackURL.isValid())
171 continue;
172 if (fallbackURL.hasFragmentIdentifier())
173 fallbackURL.removeFragmentIdentifier();
174
175 if (!protocolHostAndPortAreEqual(manifestURL, fallbackURL))
176 continue;
177
178 manifest.fallbackURLs.append(make_pair(namespaceURL, fallbackURL));
179 } else
180 ASSERT_NOT_REACHED();
181 }
182
183 return true;
184 }
185
186 }
187
188 #endif // ENABLE(OFFLINE_WEB_APPLICATIONS)
189