/* ============================================================================
 * Douglas Thrift's Search Engine License
 *
 * Copyright (C) 2002-2003, 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 Outputer
//
// Douglas Thrift
//
// $Id: Outputer.cpp,v 1.11 2003/07/20 01:46:12 douglas Exp $

#include "Outputer.h"

Outputer::Outputer(const string& headerFile, const string& bodyFile, const
	string& footerFile, const string& notfoundFile, const string& pagesFile)
{
	this->headerFile = headerFile;
	this->bodyFile = bodyFile;
	this->footerFile = footerFile;
	this->notfoundFile = notfoundFile;
	this->pagesFile = pagesFile;
}

void Outputer::output(Searcher& searcher, unsigned page)
{
	MultiSet pagesSet = searcher.getPages();
	numWebpages = pagesSet.size();
	numPages = (numWebpages + 9) / 10;
	string query = searcher.getQueryString();
	vector<string> common = searcher.getCommonUsed();

	MultiSetIterator itor = pagesSet.begin();

	for (int count = 0; count < page * 10 && itor != pagesSet.end(); count++)
	{
		itor++;
	}

	for (int index = 0; index < 10 && itor != pagesSet.end(); index++, itor++)
	{
		webpages.push_back(*itor);
	}

	this->query = searcher.getQuery().size() > 0;
	results = webpages.size() > 0;
	time = searcher.time();

	if (debug)
	{
		cerr << "query = " << this->query << "\n"
			<< "results = " << results << "\n"
			<< "time = " << duration() << "\n";
	}

	entities(query, '&', "&amp;");
	entities(query, '\"', "&quot;");
	entities(query, '<', "&lt;");
	entities(query, '>', "&gt;");

	string ignore = searcher.getIgnore();

	header(query, page, common, searcher.getAnd(), searcher.getOr(),
		ignore);

	if (results)
	{
		body();
	}
	else if (this->query)
	{
		notfound(query, searcher.getQuery().size());
	}

	footer(query, page, common, searcher.getAnd(), searcher.getOr(),
		ignore);
}

void Outputer::header(const string& query, unsigned page, vector<string>
	common, bool and_, bool or_, const string& ignore)
{
	ifstream fin(headerFile.c_str());

	string line;
	while (fin.good())
	{
		getline(fin, line);

		conditional(line, fin, "<?ifquery?>", this->query);
		conditional(line, fin, "<?ifresults?>", results);
		conditional(line, fin, "<?ifor?>", or_);
		conditional(line, fin, "<?ifand?>", and_);
		conditional(line, fin, "<?ifignore?>", ignore != "");
		conditional(line, fin, "<?ifcommon?>", common.size() == 1);
		conditional(line, fin, "<?ifmanycommon?>", common.size() > 1);

#ifndef _OpenSSL_
		tag(line, "<?version?>", programName + ' ' + programVersion + ' ' +
			platform());
#else
		tag(line, "<?version?>", programName + ' ' + programVersion + ' ' +
			platform() + ' ' + openssl());
#endif
		tag(line, "<?query?>", query);
		tag(line, "<?range?>", range(page));
		tag(line, "<?total?>", total());
		tag(line, "<?time?>", duration());
		tag(line, "<?pages?>", pages(query, page));
		tag(line, "<?ignore?>", ignore);
		tag(line, "<?common?>", common[0]);
		tag(line, "<?manycommon?>", manycommon(common));

		cout << line << (fin.good() ? "\n" : "");
	}

	fin.close();
}

void Outputer::body()
{
	for (int index = 0; index < webpages.size(); index++)
	{
		Ranker webpage = webpages[index];
		string title = webpage.getTitle();
		if (title == "")
		{
			title = webpage.getURL();
			entities(title, '&', "&amp;");
			entities(title, '\"', "&quot;");
			entities(title, '<', "&lt;");
			entities(title, '>', "&gt;");
		}
		string address = webpage.getURL();
		string sample = webpage.getSample();
		string description = webpage.getDescription();
		ostringstream size;

		size.precision(0);
		size.setf(ios_base::fixed, ios_base::floatfield);
		size << double(webpage.getSize()) / double(1024) << "k";

		entities(address, '&', "&amp;");
		entities(address, '\"', "&quot;");
		entities(address, '<', "&lt;");
		entities(address, '>', "&gt;");

		ifstream fin(bodyFile.c_str());

		string line;
		while (fin.good())
		{
			getline(fin, line);

			conditional(line, fin, "<?ifdescription?>", description != "");

			tag(line, "<?address?>", address);
			tag(line, "<?title?>", title);
			tag(line, "<?sample?>", sample);
			tag(line, "<?description?>", description);
			tag(line, "<?size?>", size.str());

			cout << line << (fin.good() ? "\n" : "");
		}

		fin.close();
	}
}

void Outputer::footer(const string& query, unsigned page, vector<string>
	common, bool and_, bool or_, const string& ignore)
{
	ifstream fin(footerFile.c_str());

	string line;
	while (fin.good())
	{
		getline(fin, line);

		conditional(line, fin, "<?ifquery?>", this->query);
		conditional(line, fin, "<?ifresults?>", results);
		conditional(line, fin, "<?ifor?>", or_);
		conditional(line, fin, "<?ifand?>", and_);
		conditional(line, fin, "<?ifignore?>", ignore != "");
		conditional(line, fin, "<?ifcommon?>", common.size() == 1);
		conditional(line, fin, "<?ifmanycommon?>", common.size() > 1);

#ifndef _OpenSSL_
		tag(line, "<?version?>", programName + ' ' + programVersion + ' ' +
			platform());
#else
		tag(line, "<?version?>", programName + ' ' + programVersion + ' ' +
			platform() + ' ' + openssl());
#endif
		tag(line, "<?query?>", query);
		tag(line, "<?range?>", range(page));
		tag(line, "<?total?>", total());
		tag(line, "<?time?>", duration());
		tag(line, "<?pages?>", pages(query, page));
		tag(line, "<?ignore?>", ignore);
		tag(line, "<?common?>", common[0]);
		tag(line, "<?manycommon?>", manycommon(common));

		cout << line << (fin.good() ? "\n" : "");
	}

	fin.close();
}

void Outputer::notfound(const string& query, unsigned keywords)
{
	ifstream fin(notfoundFile.c_str());

	string line;
	while (fin.good())
	{
		getline(fin, line);

		conditional(line, fin, "<?ifmany?>", keywords > 1);

		tag(line, "<?query?>", query);

		cout << line << (fin.good() ? "\n" : "");
	}

	fin.close();
}

string Outputer::pages(string query, unsigned page)
{
	entities(query, "&lt;", '<');
	entities(query, "&gt;", '>');
	entities(query, "&quot;", '\"');
	entities(query, "&amp;", '&');

	entities(query, '%', "%25");
	entities(query, '\t', "%09");
	entities(query, ' ', "%20");
	entities(query, '\"', "%22");
	entities(query, '#', "%23");
	entities(query, '$', "%24");
	entities(query, '&', "%26");
	entities(query, '\'', "%27");
	entities(query, '+', "%2B");
	entities(query, ',', "%2C");
	entities(query, '/', "%2F");
	entities(query, ':', "%3A");
	entities(query, ';', "%3B");
	entities(query, '<', "%3C");
	entities(query, '=', "%3D");
	entities(query, '>', "%3E");
	entities(query, '?', "%3F");
	entities(query, '@', "%40");
	entities(query, '[', "%5B");
	entities(query, ']', "%5D");
	entities(query, '\\', "%5C");
	entities(query, '^', "%5E");
	entities(query, '`', "%60");
	entities(query, '{', "%7B");
	entities(query, '|', "%7C");
	entities(query, '}', "%7D");
	entities(query, '~', "%7E");

	string lines;

	ifstream fin(pagesFile.c_str());

	string line;
	while (fin.good())
	{
		getline(fin, line);
		conditional(line, fin, "<?ifprevious?>", page >= 1);
		conditional(line, fin, "<?ifpage?>", false);
		conditional(line, fin, "<?ifnum?>", false);
		conditional(line, fin, "<?ifnext?>", false);

		ostringstream previous;

		previous << page;

		tag(line, "<?query?>", query);
		tag(line, "<?previous?>", previous.str());

		lines += line + (fin.good() ? "\n" : "");
	}

	fin.close();
	fin.clear();

	for (int index = 0; index < numPages; index++)
	{
		fin.open(pagesFile.c_str());

		while (fin.good())
		{
			getline(fin, line);
			if (index == page)
			{
				conditional(line, fin, "<?ifprevious?>", false);
				conditional(line, fin, "<?ifpage?>", true);
				conditional(line, fin, "<?ifnum?>", false);
				conditional(line, fin, "<?ifnext?>", false);

				ostringstream current;

				current << index + 1;

				tag(line, "<?page?>", current.str());
			}
			else
			{
				conditional(line, fin, "<?ifprevious?>", false);
				conditional(line, fin, "<?ifpage?>", false);
				conditional(line, fin, "<?ifnum?>", true);
				conditional(line, fin, "<?ifnext?>", false);

				ostringstream num;

				num << index + 1;

				tag(line, "<?query?>", query);
				tag(line, "<?num?>", num.str());
			}

			lines += line + (fin.good() ? "\n" : "");
		}

		fin.close();
		fin.clear();
	}

	fin.open(pagesFile.c_str());

	while (fin.good())
	{
		getline(fin, line);
		conditional(line, fin, "<?ifprevious?>", false);
		conditional(line, fin, "<?ifpage?>", false);
		conditional(line, fin, "<?ifnum?>", false);
		conditional(line, fin, "<?ifnext?>", page + 2 <= numPages);

		ostringstream next;

		next << page + 2;

		tag(line, "<?query?>", query);
		tag(line, "<?next?>", next.str());

		lines += line + (fin.good() ? "\n" : "");
	}

	fin.close();

	return lines;
}

string Outputer::range(unsigned page)
{
	unsigned bottom = page * 10 + 1;
	unsigned top = numWebpages > page * 10 + 10 ? page * 10 + 10 : numWebpages;
	ostringstream range;

	range << bottom << " - " << top;

	return range.str();
}

string Outputer::total()
{
	ostringstream total;

	total << numWebpages;

	return total.str();
}

string Outputer::duration()
{
	ostringstream duration;

	duration.precision(2);
	duration << time;

	return duration.str();
}

string Outputer::manycommon(vector<string> common)
{
	string line;

	for (int index = 0; index < common.size(); index++)
	{
		line += common[index];

		if (index != common.size() - 1) line += ' ';
	}

	return line;
}

void Outputer::tag(string& line, char* tag, const string& replacement)
{
	int begin = 0;
	while (begin < line.length())
	{
		int spot = line.find(tag, begin);

		if (spot != string::npos)
		{
			line.replace(spot, strlen(tag), replacement);
		}
		else
		{
			break;
		}

		begin = spot + replacement.length();
	}
}

void Outputer::conditional(string& line, ifstream& fin, char* tag, bool
	condition)
{
	unsigned begin = 0;
	while (begin < line.length())
	{
		unsigned start = line.find(tag, begin);
		unsigned finish = line.find("<?endif?>", start);

		if (start == string::npos) break;

		string next;
		while (finish == string::npos)
		{
			getline(fin, next);
			line += '\n' + next;
			finish = line.find("<?endif?>", start);
		}

		if (condition)
		{
			line.erase(start, strlen(tag));
			line.erase(finish - strlen(tag), 9);

			begin = finish - strlen(tag) - 9;
		}
		else
		{
			line.erase(start, finish - start + 9);

			begin = start;
		}
	}
}