| 1 |
douglas |
1 |
/* ============================================================================ |
| 2 |
|
|
* Douglas Thrift's Search Engine License |
| 3 |
|
|
* |
| 4 |
douglas |
312 |
* Copyright (C) 2002-2004, Douglas Thrift. All Rights Reserved. |
| 5 |
douglas |
1 |
* 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 Indexer |
| 46 |
|
|
// |
| 47 |
|
|
// Douglas Thrift |
| 48 |
|
|
// |
| 49 |
Douglas Thrift |
331 |
// $Id$ |
| 50 |
douglas |
1 |
|
| 51 |
Douglas Thrift |
334 |
#ifndef _Indexer_hpp_ |
| 52 |
|
|
#define _Indexer_hpp_ |
| 53 |
douglas |
1 |
|
| 54 |
Douglas Thrift |
334 |
#include "Search.hpp" |
| 55 |
|
|
#include "URL.hpp" |
| 56 |
|
|
#include "Page.hpp" |
| 57 |
|
|
#include "HttpHandler.hpp" |
| 58 |
|
|
#include "Processor.hpp" |
| 59 |
douglas |
1 |
|
| 60 |
|
|
typedef set<string> Set; |
| 61 |
|
|
typedef set<string>::iterator SetIterator; |
| 62 |
|
|
|
| 63 |
|
|
class Indexer |
| 64 |
|
|
{ |
| 65 |
|
|
private: |
| 66 |
|
|
enum robot { none, version, name, all }; |
| 67 |
|
|
HttpHandler http; |
| 68 |
|
|
Processor processor; |
| 69 |
|
|
Set pages; |
| 70 |
|
|
queue<URL> links; |
| 71 |
douglas |
25 |
queue<string> referers; |
| 72 |
douglas |
1 |
string indexFile; |
| 73 |
|
|
Set domains; |
| 74 |
|
|
Set restrictions; |
| 75 |
|
|
Set checked; |
| 76 |
douglas |
25 |
void index(URL& url, ofstream& fout, const string referer = ""); |
| 77 |
douglas |
1 |
bool restricted(URL& url); |
| 78 |
|
|
void robots(URL& url); |
| 79 |
|
|
public: |
| 80 |
douglas |
37 |
Indexer(string& indexFile, set<string>& domains, set<string>& |
| 81 |
|
|
restrictions); |
| 82 |
douglas |
1 |
~Indexer() {} |
| 83 |
|
|
void index(string& begin); |
| 84 |
|
|
}; |
| 85 |
|
|
|
| 86 |
Douglas Thrift |
334 |
#endif // _Indexer_hpp_ |
