// Parser.cpp : Defines the entry point for the console application.
//

#include "stdafx.h"
#include <vector>
#include <string>
#include <sstream>
#include <fstream>
#include <iostream>
#include <regex>

const std::string START_FROM = "\"extract\":\"";

std::string GetData() {
	std::ifstream t("E:\\data.txt");
	std::stringstream buffer;
	buffer << t.rdbuf();
	std::string input = buffer.str();

	std::string::size_type loc = input.find(START_FROM, 0);
	input = input.substr(loc + START_FROM.size(), input.size() - loc - START_FROM.size() - 5);
	return input;
}

typedef std::string String;

static enum Tags {
	CLOSE = -1,
	P,
	H2,
	H3
};

short tagDetect(char * ptr){
	if (*ptr == '/') {
		return 0;
	}

	if (*ptr == 'p') {
		return 1;
	}

	if (*(ptr + 1) == '2')
		return 2;

	if (*(ptr + 1) == '3')
		return 3;

	return -1;
}


struct Node {
	short tag;
	std::string data;

	Node(std::string input, short tagId) {
		tag = tagId;
		data = input;
	}
};

int _tmain(int argc, _TCHAR* argv[])
{
	std::string input = GetData();
	std::vector<Node> elems;

	String::size_type pos = 0;
	char pattern = '<';

	int openPos;
	short tagID, lastTag;

	double  duration;
	clock_t start = clock();

	for (int i = 0; i < 20000; i++) {
		elems.clear();

		pos = 0;
		while ((pos = input.find(pattern, pos)) != std::string::npos) {
			pos++;
			tagID = tagDetect(&input[pos]);
			switch (tagID) {
			case 0:
				if (tagID = tagDetect(&input[pos + 1]) == lastTag && pos - openPos > 10) {
					elems.push_back(Node(input.substr(openPos + (lastTag > 1 ? 3 : 2), pos - openPos - (lastTag > 1 ? 3 : 2) - 1), lastTag));
				}

				break;
			case 1:
			case 2:
			case 3:
				openPos = pos;
				lastTag = tagID;
				break;
			}
		}

	}

	duration = (double)(clock() - start) / CLOCKS_PER_SEC;
	printf("%2.1f seconds\n", duration);

	getchar();

	for (int i = 0; i < elems.size(); i++) {
		std::cout << elems[i].data << " - " << elems[i].tag << std::endl;
	}

	getchar();

	return 0;
}


/*
void clock() {
	long i = 600000000L;
	clock_t start, finish;
	double  duration;

	printf("Time to do %ld empty loops is ", i);
	start = clock();
	while (i--)
		;
	finish = clock();
	duration = (double)(finish - start) / CLOCKS_PER_SEC;
	printf("%2.1f seconds\n", duration);
}
*/