trunk/Search/URL.cpp

/* ============================================================================
 * Douglas Thrift's Search Engine License
 *
 * Copyright (C) 2002-2004, Douglas Thrift. All Rights Reserved.
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright notice,
 *    this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright notice,
 *    this list of conditions and the following disclaimer in the documentation
 *    and/or other materials provided with the distribution.
 *
 * 3. The end-user documentation included with the redistribution, if any, must
 *    include the following acknowledgment:
 *
 *       "This product includes software developed by Douglas Thrift
 *       (http://computers.douglasthrift.net/searchengine/)."
 *
 *    Alternately, this acknowledgment may appear in the software itself, if
 *    and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Douglas Thrift" and "Douglas Thrift's Search Engine" must not
 *    be used to endorse or promote products derived from this software without
 *    specific prior written permission.  For written permission, please visit
 *    http://www.douglasthrift.net/contact.cgi for contact information.
 *
 * 5. Products derived from this software may not be called "Douglas Thrift's
 *    Search Engine", nor may "Douglas Thrift's Search Engine" appear in their
 *    name, without prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
 * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
 * FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA,
 * OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
 * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 * ============================================================================
 */
// Douglas Thrift's Search Engine URL
//
// Douglas Thrift
//
// $Id$

#include "URL.h"

URL::URL(const string& url)
{
        setURL(url);
}

URL::URL(const string& address, unsigned port, const string& path)
{
        this->address = address;
        this->port = port;
        this->path = path;
#ifdef _OpenSSL_
        tls = false;
#endif
}

#ifdef _OpenSSL_
URL::URL(const string& address, unsigned port, const string& path, bool tls)
{
        this->address = address;
        this->port = port;
        this->path = path;
        this->tls = tls;
}
#endif

string URL::getURL()
{
        ostringstream url;
#ifndef _OpenSSL_
        url << "http://" << address;

        if (port != 80)
#else
        url << (tls ? "https://" : "http://") << address;

        if (port != 80 && !tls || port != 443 && tls)
#endif
        {
                url << ":" << port;
        }

        url << path;

        return url.str();
}

void URL::setURL(const URL& url)
{
        this->address = url.address;
        this->port = url.port;
        this->path = url.path;
#ifdef _OpenSSL_
        this->tls = url.tls;
#endif
}

void URL::setURL(const string& url)
{
#ifndef _OpenSSL_
        if (url.find("http://") != 0 || url.length() <= 7)
        {
                cerr << program << ": Malformed URL: " << url << "\n";
                exit(1);
        }

        unsigned begin = 7;
#else
        tls = false;

        if (url.find("https://") == 0 && url.length() > 8)
        {
                tls = true;
        }
        else if (url.find("http://") != 0 || url.length() <= 7)
        {
                cerr << program << ": Malformed URL: " << url << "\n";
                exit(1);
        }

        unsigned begin = tls ? 8 : 7;
#endif
        unsigned colon = url.find(':', begin);
        unsigned end = url.find('/', begin);

        if (colon != string::npos && colon < end)
        {
                address = url.substr(begin, colon - begin);

                istringstream number((url.substr(colon + 1, end - colon - 1)));

                number >> port;
        }
        else
        {
                address = url.substr(begin, end - begin);
#ifndef _OpenSSL_
                port = 80;
#else
                port = tls ? 443 : 80;
#endif
        }

        if (end == string::npos)
        {
                path = "/";
        }
        else
        {
                path = url.substr(end);
        }
}

void URL::setPath(const string& path)
{
        if (path.find('/') != 0)
        {
                this->path = "/" + path;
        }
        else
        {
                this->path = path;
        }
}

ostream& operator<<(ostream& os, URL& data)
{
        os << data.getURL();

        return os;
}

string getLink(string link, URL& url)
{
        string hyperlink = "";

        if (link.find('#') != string::npos)
        {
                unsigned pound = link.find('#');
                link.erase(pound);
        }

        if (link.find("://") != string::npos)
        {
#ifndef _OpenSSL_
                if (link.find("http://") == 0 && link.length() > 7) hyperlink = link;
#else
                if (link.find("http://") == 0 && link.length() > 7 ||
                        link.find("https://") == 0 && link.length() > 8) hyperlink = link;
#endif
        }
        else if (link.find("mailto:") == 0)
        {
                // do nothing we are not evil spammers!
        }
        else if (link.find("news:") == 0)
        {
                // do nothing this isn't Google Groups
        }
        else if (link.find("//") == 0)
        {
#ifndef _OpenSSL_
                hyperlink = "http:" + link;
#else
                hyperlink = (url.getTls() ? "https:" : "http:") + link;
#endif
        }
        else if (link.find('/') == 0)
        {
                hyperlink = url.getURL();

#ifndef _OpenSSL_
                unsigned path = hyperlink.find('/', 7);
#else
                unsigned path = hyperlink.find('/', url.getTls() ? 8 : 7);
#endif
                hyperlink.erase(path);

                hyperlink += link;
        }
        else if (link == "")
        {
                // a blank link is useless
        }
        else
        {
                hyperlink = url.getURL();
                string path = url.getPath();

                unsigned cutoff = hyperlink.rfind(path);
                hyperlink.erase(cutoff);

                unsigned dir = path.rfind('/') + 1;
                path.erase(dir);

                while (link.find("../") == 0)
                {
                        unsigned dot = path.rfind('/') - 1;
                        unsigned up = path.rfind('/', dot) + 1;

                        path.erase(up);
                        link.erase(0, 3);
                }
                while (link.find("./") == 0)
                {
                        link.erase(0, 2);
                }

                hyperlink += path + link;
        }

        return hyperlink;
}
Revision:	331
Committed:	2004-04-05T15:50:25-07:00 (21 years, 2 months ago) by Douglas Thrift
File size:	6114 byte(s)
Log Message:	It's Subversion time!
#	Content
1	/* ============================================================================
2	* Douglas Thrift's Search Engine License
3	*
4	* Copyright (C) 2002-2004, 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.h"
52
53	URL::URL(const string& url)
54	{
55	setURL(url);
56	}
57
58	URL::URL(const string& address, unsigned port, const string& path)
59	{
60	this->address = address;
61	this->port = port;
62	this->path = path;
63	#ifdef _OpenSSL_
64	tls = false;
65	#endif
66	}
67
68	#ifdef _OpenSSL_
69	URL::URL(const string& address, unsigned port, const string& path, bool tls)
70	{
71	this->address = address;
72	this->port = port;
73	this->path = path;
74	this->tls = tls;
75	}
76	#endif
77
78	string URL::getURL()
79	{
80	ostringstream url;
81	#ifndef _OpenSSL_
82	url << "http://" << address;
83
84	if (port != 80)
85	#else
86	url << (tls ? "https://" : "http://") << address;
87
88	if (port != 80 && !tls \|\| port != 443 && tls)
89	#endif
90	{
91	url << ":" << port;
92	}
93
94	url << path;
95
96	return url.str();
97	}
98
99	void URL::setURL(const URL& url)
100	{
101	this->address = url.address;
102	this->port = url.port;
103	this->path = url.path;
104	#ifdef _OpenSSL_
105	this->tls = url.tls;
106	#endif
107	}
108
109	void URL::setURL(const string& url)
110	{
111	#ifndef _OpenSSL_
112	if (url.find("http://") != 0 \|\| url.length() <= 7)
113	{
114	cerr << program << ": Malformed URL: " << url << "\n";
115	exit(1);
116	}
117
118	unsigned begin = 7;
119	#else
120	tls = false;
121
122	if (url.find("https://") == 0 && url.length() > 8)
123	{
124	tls = true;
125	}
126	else if (url.find("http://") != 0 \|\| url.length() <= 7)
127	{
128	cerr << program << ": Malformed URL: " << url << "\n";
129	exit(1);
130	}
131
132	unsigned begin = tls ? 8 : 7;
133	#endif
134	unsigned colon = url.find(':', begin);
135	unsigned end = url.find('/', begin);
136
137	if (colon != string::npos && colon < end)
138	{
139	address = url.substr(begin, colon - begin);
140
141	istringstream number((url.substr(colon + 1, end - colon - 1)));
142
143	number >> port;
144	}
145	else
146	{
147	address = url.substr(begin, end - begin);
148	#ifndef _OpenSSL_
149	port = 80;
150	#else
151	port = tls ? 443 : 80;
152	#endif
153	}
154
155	if (end == string::npos)
156	{
157	path = "/";
158	}
159	else
160	{
161	path = url.substr(end);
162	}
163	}
164
165	void URL::setPath(const string& path)
166	{
167	if (path.find('/') != 0)
168	{
169	this->path = "/" + path;
170	}
171	else
172	{
173	this->path = path;
174	}
175	}
176
177	ostream& operator<<(ostream& os, URL& data)
178	{
179	os << data.getURL();
180
181	return os;
182	}
183
184	string getLink(string link, URL& url)
185	{
186	string hyperlink = "";
187
188	if (link.find('#') != string::npos)
189	{
190	unsigned pound = link.find('#');
191	link.erase(pound);
192	}
193
194	if (link.find("://") != string::npos)
195	{
196	#ifndef _OpenSSL_
197	if (link.find("http://") == 0 && link.length() > 7) hyperlink = link;
198	#else
199	if (link.find("http://") == 0 && link.length() > 7 \|\|
200	link.find("https://") == 0 && link.length() > 8) hyperlink = link;
201	#endif
202	}
203	else if (link.find("mailto:") == 0)
204	{
205	// do nothing we are not evil spammers!
206	}
207	else if (link.find("news:") == 0)
208	{
209	// do nothing this isn't Google Groups
210	}
211	else if (link.find("//") == 0)
212	{
213	#ifndef _OpenSSL_
214	hyperlink = "http:" + link;
215	#else
216	hyperlink = (url.getTls() ? "https:" : "http:") + link;
217	#endif
218	}
219	else if (link.find('/') == 0)
220	{
221	hyperlink = url.getURL();
222
223	#ifndef _OpenSSL_
224	unsigned path = hyperlink.find('/', 7);
225	#else
226	unsigned path = hyperlink.find('/', url.getTls() ? 8 : 7);
227	#endif
228	hyperlink.erase(path);
229
230	hyperlink += link;
231	}
232	else if (link == "")
233	{
234	// a blank link is useless
235	}
236	else
237	{
238	hyperlink = url.getURL();
239	string path = url.getPath();
240
241	unsigned cutoff = hyperlink.rfind(path);
242	hyperlink.erase(cutoff);
243
244	unsigned dir = path.rfind('/') + 1;
245	path.erase(dir);
246
247	while (link.find("../") == 0)
248	{
249	unsigned dot = path.rfind('/') - 1;
250	unsigned up = path.rfind('/', dot) + 1;
251
252	path.erase(up);
253	link.erase(0, 3);
254	}
255	while (link.find("./") == 0)
256	{
257	link.erase(0, 2);
258	}
259
260	hyperlink += path + link;
261	}
262
263	return hyperlink;
264	}