Search/trunk/URL.cpp

/* ============================================================================
 * Douglas Thrift's Search Engine License
 *
 * Copyright (C) 2002, 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
//
// URL.cpp

#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;
}

string URL::getURL()
{
        string url = "http://" + address;

        if (port != 80)
        {
                char* cport = new char[1024];

                sprintf(cport, "%u", port);

                url += string(":") + cport;

                delete [] cport;
        }

        url += path;

        return url;
}

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

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

        int begin = 7;
        int colon = url.find(':', begin);
        int end = url.find('/', begin);

        if (colon != string::npos && colon < end)
        {
                address = url.substr(begin, colon - begin);
                port = strtoul(url.substr(colon + 1, end - colon - 1).c_str(), 0, 0);
        }
        else
        {
                address = url.substr(begin, end - begin);
                port = 80;
        }

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

void URL::setAddress(const string& address)
{
        this->address = address;
}

void URL::setPort(unsigned port)
{
        this->port = port;
}

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)
        {
                if (link.find("http://") == 0) hyperlink = link;
        }
        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)
        {
                hyperlink = "http:" + link;
        }
        else if (link.find('/') == 0)
        {
                hyperlink = url.getURL();

                unsigned path = hyperlink.find('/', 7);
                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:	18
Committed:	2002-12-09T21:40:12-08:00 (22 years, 6 months ago) by douglas
Original Path:	*trunk/Search/URL.cpp*
File size:	5182 byte(s)
Log Message:	Implemented more HttpHandler stuff. Added news: protocol to those ignored by getLink().
#	User	Rev	Content
1	douglas	1	/* ============================================================================
2			* Douglas Thrift's Search Engine License
3			*
4			* Copyright (C) 2002, 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			// URL.cpp
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			}
64
65			string URL::getURL()
66			{
67			string url = "http://" + address;
68
69			if (port != 80)
70			{
71			char* cport = new char[1024];
72
73			sprintf(cport, "%u", port);
74
75			url += string(":") + cport;
76
77			delete [] cport;
78			}
79
80			url += path;
81
82			return url;
83			}
84
85			void URL::setURL(const URL& url)
86			{
87			this->address = url.address;
88			this->port = url.port;
89			this->path = url.path;
90			}
91
92			void URL::setURL(const string& url)
93			{
94			if (url.find("http://") \|\| url.length() <= 7)
95			{
96			cerr << program << ": Malformed URL: " << url << "\n";
97			exit(1);
98			}
99
100			int begin = 7;
101			int colon = url.find(':', begin);
102			int end = url.find('/', begin);
103
104			if (colon != string::npos && colon < end)
105			{
106			address = url.substr(begin, colon - begin);
107			port = strtoul(url.substr(colon + 1, end - colon - 1).c_str(), 0, 0);
108			}
109			else
110			{
111			address = url.substr(begin, end - begin);
112			port = 80;
113			}
114
115			if (end == string::npos)
116			{
117			path = "/";
118			}
119			else
120			{
121			path = url.substr(end);
122			}
123			}
124
125			void URL::setAddress(const string& address)
126			{
127			this->address = address;
128			}
129
130			void URL::setPort(unsigned port)
131			{
132			this->port = port;
133			}
134
135			void URL::setPath(const string& path)
136			{
137			if (path.find('/') != 0)
138			{
139			this->path = "/" + path;
140			}
141			else
142			{
143			this->path = path;
144			}
145			}
146
147			ostream& operator<<(ostream& os, URL& data)
148			{
149			os << data.getURL();
150
151			return os;
152			}
153	douglas	17
154			string getLink(string link, URL& url)
155			{
156			string hyperlink = "";
157
158			if (link.find('#') != string::npos)
159			{
160			unsigned pound = link.find('#');
161			link.erase(pound);
162			}
163
164			if (link.find("://") != string::npos)
165			{
166			if (link.find("http://") == 0) hyperlink = link;
167			}
168			else if (link.find("mailto:") == 0)
169			{
170			// do nothing we are not evil spammers!
171			}
172	douglas	18	else if (link.find("news:") == 0)
173			{
174			// do nothing this isn't Google Groups
175			}
176	douglas	17	else if (link.find("//") == 0)
177			{
178			hyperlink = "http:" + link;
179			}
180			else if (link.find('/') == 0)
181			{
182			hyperlink = url.getURL();
183
184			unsigned path = hyperlink.find('/', 7);
185			hyperlink.erase(path);
186
187			hyperlink += link;
188			}
189			else if (link == "")
190			{
191			// a blank link is useless
192			}
193			else
194			{
195			hyperlink = url.getURL();
196			string path = url.getPath();
197
198			unsigned cutoff = hyperlink.rfind(path);
199			hyperlink.erase(cutoff);
200
201			unsigned dir = path.rfind('/') + 1;
202			path.erase(dir);
203
204			while (link.find("../") == 0)
205			{
206			unsigned dot = path.rfind('/') - 1;
207			unsigned up = path.rfind('/', dot) + 1;
208
209			path.erase(up);
210			link.erase(0, 3);
211			}
212			while (link.find("./") == 0)
213			{
214			link.erase(0, 2);
215			}
216
217			hyperlink += path + link;
218			}
219
220			return hyperlink;
221			}