| 1 |
/* ============================================================================ |
| 2 |
* Douglas Thrift's Search Engine License |
| 3 |
* |
| 4 |
* Copyright (C) 2002-2004, 2008, Douglas Thrift. All Rights Reserved. |
| 5 |
* Redistribution and use in source and binary forms, with or without |
| 6 |
* modification, are permitted provided that the following conditions are met: |
| 7 |
* |
| 8 |
* 1. Redistributions of source code must retain the above copyright notice, |
| 9 |
* this list of conditions and the following disclaimer. |
| 10 |
* |
| 11 |
* 2. Redistributions in binary form must reproduce the above copyright notice, |
| 12 |
* this list of conditions and the following disclaimer in the documentation |
| 13 |
* and/or other materials provided with the distribution. |
| 14 |
* |
| 15 |
* 3. The end-user documentation included with the redistribution, if any, must |
| 16 |
* include the following acknowledgment: |
| 17 |
* |
| 18 |
* "This product includes software developed by Douglas Thrift |
| 19 |
* (http://computers.douglasthrift.net/searchengine/)." |
| 20 |
* |
| 21 |
* Alternately, this acknowledgment may appear in the software itself, if |
| 22 |
* and wherever such third-party acknowledgments normally appear. |
| 23 |
* |
| 24 |
* 4. The names "Douglas Thrift" and "Douglas Thrift's Search Engine" must not |
| 25 |
* be used to endorse or promote products derived from this software without |
| 26 |
* specific prior written permission. For written permission, please visit |
| 27 |
* http://www.douglasthrift.net/contact.cgi for contact information. |
| 28 |
* |
| 29 |
* 5. Products derived from this software may not be called "Douglas Thrift's |
| 30 |
* Search Engine", nor may "Douglas Thrift's Search Engine" appear in their |
| 31 |
* name, without prior written permission. |
| 32 |
* |
| 33 |
* THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, |
| 34 |
* INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND |
| 35 |
* FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
| 36 |
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
| 37 |
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 38 |
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, |
| 39 |
* OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF |
| 40 |
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING |
| 41 |
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, |
| 42 |
* EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 43 |
* ============================================================================ |
| 44 |
*/ |
| 45 |
// Douglas Thrift's Search Engine URL |
| 46 |
// |
| 47 |
// Douglas Thrift |
| 48 |
// |
| 49 |
// $Id$ |
| 50 |
|
| 51 |
#include "URL.hpp" |
| 52 |
|
| 53 |
string URL::getURL() |
| 54 |
{ |
| 55 |
ostringstream url; |
| 56 |
|
| 57 |
#ifndef _OpenSSL_ |
| 58 |
url << "http://" << address; |
| 59 |
|
| 60 |
if (port != 80) |
| 61 |
#else |
| 62 |
url << (tls ? "https://" : "http://") << address; |
| 63 |
|
| 64 |
if (port != 80 && !tls || port != 443 && tls) |
| 65 |
#endif |
| 66 |
{ |
| 67 |
url << ":" << port; |
| 68 |
} |
| 69 |
|
| 70 |
url << path; |
| 71 |
|
| 72 |
return url.str(); |
| 73 |
} |
| 74 |
|
| 75 |
void URL::setURL(const URL& url) |
| 76 |
{ |
| 77 |
this->address = url.address; |
| 78 |
this->port = url.port; |
| 79 |
this->path = url.path; |
| 80 |
#ifdef _OpenSSL_ |
| 81 |
this->tls = url.tls; |
| 82 |
#endif |
| 83 |
} |
| 84 |
|
| 85 |
void URL::setURL(const string& url) |
| 86 |
{ |
| 87 |
#ifndef _OpenSSL_ |
| 88 |
if (url.find("http://") != 0 || url.length() <= 7) |
| 89 |
{ |
| 90 |
cerr << program << ": Malformed URL: " << url << "\n"; |
| 91 |
|
| 92 |
exit(1); |
| 93 |
} |
| 94 |
|
| 95 |
size_t begin(7); |
| 96 |
|
| 97 |
#else |
| 98 |
tls = false; |
| 99 |
|
| 100 |
if (url.find("https://") == 0 && url.length() > 8) |
| 101 |
{ |
| 102 |
tls = true; |
| 103 |
} |
| 104 |
else if (url.find("http://") != 0 || url.length() <= 7) |
| 105 |
{ |
| 106 |
cerr << program << ": Malformed URL: " << url << "\n"; |
| 107 |
|
| 108 |
exit(1); |
| 109 |
} |
| 110 |
|
| 111 |
size_t begin(tls ? 8 : 7); |
| 112 |
#endif |
| 113 |
|
| 114 |
size_t colon(url.find(':', begin)), end(url.find('/', begin)); |
| 115 |
|
| 116 |
if (colon != string::npos && colon < end) |
| 117 |
{ |
| 118 |
address = url.substr(begin, colon - begin); |
| 119 |
|
| 120 |
istringstream number((url.substr(colon + 1, end - colon - 1))); |
| 121 |
|
| 122 |
number >> port; |
| 123 |
} |
| 124 |
else |
| 125 |
{ |
| 126 |
address = url.substr(begin, end - begin); |
| 127 |
#ifndef _OpenSSL_ |
| 128 |
port = 80; |
| 129 |
#else |
| 130 |
port = tls ? 443 : 80; |
| 131 |
#endif |
| 132 |
} |
| 133 |
|
| 134 |
if (end == string::npos) |
| 135 |
{ |
| 136 |
path = "/"; |
| 137 |
} |
| 138 |
else |
| 139 |
{ |
| 140 |
path = url.substr(end); |
| 141 |
} |
| 142 |
} |
| 143 |
|
| 144 |
void URL::setPath(const string& path) |
| 145 |
{ |
| 146 |
if (path.find('/') != 0) |
| 147 |
{ |
| 148 |
this->path = "/" + path; |
| 149 |
} |
| 150 |
else |
| 151 |
{ |
| 152 |
this->path = path; |
| 153 |
} |
| 154 |
} |
| 155 |
|
| 156 |
ostream& operator<<(ostream& os, URL& data) |
| 157 |
{ |
| 158 |
os << data.getURL(); |
| 159 |
|
| 160 |
return os; |
| 161 |
} |
| 162 |
|
| 163 |
string getLink(string link, URL& url) |
| 164 |
{ |
| 165 |
string hyperlink; |
| 166 |
|
| 167 |
if (link.find('#') != string::npos) |
| 168 |
{ |
| 169 |
size_t pound(link.find('#')); |
| 170 |
|
| 171 |
link.erase(pound); |
| 172 |
} |
| 173 |
|
| 174 |
if (link.find("://") != string::npos) |
| 175 |
{ |
| 176 |
#ifndef _OpenSSL_ |
| 177 |
if (link.find("http://") == 0 && link.length() > 7) hyperlink = link; |
| 178 |
#else |
| 179 |
if (link.find("http://") == 0 && link.length() > 7 |
| 180 |
|| link.find("https://") == 0 && link.length() > 8) |
| 181 |
hyperlink = link; |
| 182 |
#endif |
| 183 |
} |
| 184 |
else if (link.find("mailto:") == 0) |
| 185 |
{ |
| 186 |
// do nothing we are not evil spammers! |
| 187 |
} |
| 188 |
else if (link.find("news:") == 0) |
| 189 |
{ |
| 190 |
// do nothing this isn't Google Groups |
| 191 |
} |
| 192 |
else if (link.find("aim:") == 0) |
| 193 |
{ |
| 194 |
// do nothing we don't do AIM |
| 195 |
} |
| 196 |
else if (link.find("//") == 0) |
| 197 |
{ |
| 198 |
#ifndef _OpenSSL_ |
| 199 |
hyperlink = "http:" + link; |
| 200 |
#else |
| 201 |
hyperlink = (url.getTls() ? "https:" : "http:") + link; |
| 202 |
#endif |
| 203 |
} |
| 204 |
else if (link.find('/') == 0) |
| 205 |
{ |
| 206 |
hyperlink = url.getURL(); |
| 207 |
|
| 208 |
#ifndef _OpenSSL_ |
| 209 |
size_t path(hyperlink.find('/', 7)); |
| 210 |
#else |
| 211 |
size_t path(hyperlink.find('/', url.getTls() ? 8 : 7)); |
| 212 |
#endif |
| 213 |
|
| 214 |
hyperlink.erase(path); |
| 215 |
|
| 216 |
hyperlink += link; |
| 217 |
} |
| 218 |
else if (link.empty()) |
| 219 |
{ |
| 220 |
// a blank link is useless |
| 221 |
} |
| 222 |
else |
| 223 |
{ |
| 224 |
hyperlink = url.getURL(); |
| 225 |
|
| 226 |
string path(url.getPath()); |
| 227 |
size_t cutoff(hyperlink.rfind(path)); |
| 228 |
|
| 229 |
hyperlink.erase(cutoff); |
| 230 |
|
| 231 |
size_t dir(path.rfind('/') + 1); |
| 232 |
|
| 233 |
path.erase(dir); |
| 234 |
|
| 235 |
while (link.find("../") == 0) |
| 236 |
{ |
| 237 |
size_t dot(path.rfind('/') - 1), up(path.rfind('/', dot) + 1); |
| 238 |
|
| 239 |
path.erase(up); |
| 240 |
link.erase(0, 3); |
| 241 |
} |
| 242 |
while (link.find("./") == 0) |
| 243 |
{ |
| 244 |
link.erase(0, 2); |
| 245 |
} |
| 246 |
|
| 247 |
hyperlink += path + link; |
| 248 |
} |
| 249 |
|
| 250 |
return hyperlink; |
| 251 |
} |
