/* ============================================================================
 * 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 Searcher
//
// Douglas Thrift
//
// Searcher.cpp

#include "Searcher.h"

Searcher::Searcher(string& queryString)
{
	setCommon();
	setAnd(false);
	setOr(false);

	this->queryString = queryString;

	setQuery();
}

void Searcher::search(vector<string> indices)
{
	start = clock();

	const string XMLTYPE = "<?xml version=\"1.0\" encoding=\"ISO-8859-1\" stan"
		+ string("dalone=\"no\"?>");
	const string DOCTYPE = "<!DOCTYPE index SYSTEM \"index.dtd\">";

	if (query.size() > 0)
	{
		for (int index = 0; index < indices.size(); index++)
		{
			ifstream fin(indices[index].c_str());

			if (!fin.is_open())
			{
				cerr << program << ": Could not open index file: "
					<< indices[index] << "\n";
				fin.clear();

				continue;
			}

			string line;

			getline(fin, line);
			if (line != XMLTYPE)
			{
				cerr << program << ": Invalid XML version declaration: "
					<< indices[index] << "\n";
				fin.close();
				fin.clear();

				continue;
			}

			getline(fin, line);
			if (line != DOCTYPE)
			{
				cerr << program << ": Invalid XML doctype: " << indices[index]
					<< "\n";
				fin.close();
				fin.clear();
				continue;
			}

			getline(fin, line);
			if (line != "<index>")
			{
				cerr << program << ": Invalid XML root element: "
					<< indices[index] << "\n";
				fin.close();
				fin.clear();
				continue;
			}

			while (fin.good())
			{
				Page page;

				fin >> page;

				if (!page.empty()) search(page);
			}

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

	finish = clock();
}

void Searcher::search(Page& page)
{
	Ranker ranker(page);
	ranker.rank(query);

	if (ranker != 0)
	{
		ranker.setSample();
		pages.insert(ranker);
	}
}

void Searcher::setQuery()
{
	string queryStringNormal = queryString;
	normalize(queryStringNormal);

	if (debug) cerr << "queryString = " << queryString << "\n"
		<< "queryStringNormal = " << queryStringNormal << "\n";

	unsigned begin = 0;
	bool capitalOr = false, quotes = false;
	while (begin < queryStringNormal.length())
	{
		string word;

		unsigned beginQuote = queryStringNormal.find('\"', begin);
		unsigned endQuote = beginQuote != string::npos ?
			queryStringNormal.find('\"', beginQuote + 1) : string::npos;
		unsigned space = queryStringNormal.find(' ', begin);

		if (beginQuote == begin)
		{
			quotes = true;
			word = queryStringNormal.substr(beginQuote + 1, endQuote -
				beginQuote - 1);
		}
		else if (beginQuote == (begin + 8) && queryStringNormal.substr(begin, 8
			) == "intitle:")
		{
			quotes = true;
			word = "intitle:" + queryStringNormal.substr(beginQuote + 1,
				endQuote - beginQuote - 1);
			beginQuote = begin;
		}
		else if (beginQuote == (begin + 6) && queryStringNormal.substr(begin, 6
			) == "inurl:")
		{
			quotes = true;
			word = "inurl:" + queryStringNormal.substr(beginQuote + 1, endQuote
				- beginQuote - 1);
			beginQuote = begin;
		}
		else if (beginQuote == (begin + 7) && queryStringNormal.substr(begin, 7
			) == "intext:")
		{
			quotes = true;
			word = "intext:" + queryStringNormal.substr(beginQuote + 1,
				endQuote - beginQuote - 1);
			beginQuote = begin;
		}
		else
		{
			quotes = false;
			word = queryStringNormal.substr(begin, space - begin);
		}

		if (word != "")
		{
			string lowerWord(word.length(), ' ');

			for (unsigned index = 0; index < word.length(); index++)
			{
				lowerWord[index] = tolower(word[index]);
			}

			if (debug) cerr << "word = " << word << "\n"
				<< "lowerWord = " << lowerWord << "\n";

			if (word == "OR" && !quotes)
			{
				capitalOr = true;
				query[query.size() - 1] += " OR";
			}
			else if (lowerWord == "or" && !quotes)
			{
				setOr(true);
			}
			else if (lowerWord == "and" && !quotes)
			{
				setAnd(true);
			}
			else if (common.find(lowerWord) != common.end() && !quotes)
			{
				commonUsed.push_back(word);
			}
			else
			{
				if (capitalOr) capitalOr = false;
				if (query.size() < 10)
				{
					query.push_back(lowerWord);
				}
				else
				{
					setIgnore(lowerWord);

					if (debug) cerr << "ignore = " << ignore << "\n";

					break;
				}
			}
		}

		if (endQuote == string::npos && space == string::npos)
		{
			begin = string::npos;
		}
		else if (beginQuote == begin && endQuote != string::npos)
		{
			begin = endQuote + 1;
		}
		else
		{
			begin = space + 1;
		}
	}

	if (debug)
	{
		cerr << "query = {\n";

		for (unsigned index = 0; index < query.size(); index++)
		{
			cerr << "   [" << index << "] = " << query[index] << "\n";
		}

		cerr << "}\n";
	}
}

void Searcher::setCommon()
{
	common.insert("&");
	common.insert("a");
	common.insert("about");
	common.insert("an");
	// "and" has its own special message
//	common.insert("and");
	common.insert("are");
	common.insert("as");
	common.insert("at");
	common.insert("be");
	common.insert("by");
	common.insert("com");
	common.insert("from");
	common.insert("how");
	common.insert("i");
	common.insert("in");
	common.insert("is");
	common.insert("it");
	common.insert("of");
	common.insert("on");
	// "or" has its own special message
//	common.insert("or");
	common.insert("that");
	common.insert("the");
	common.insert("this");
	common.insert("to");
	common.insert("was");
	common.insert("what");
	common.insert("when");
	common.insert("where");
	common.insert("which");
	common.insert("who");
	common.insert("why");
	common.insert("will");
	common.insert("with");
}