C++ Boost regex

boost-regex-test.cpp

#include <string> 
#include <iostream> 
#include <boost/regex.hpp>
#include <boost/spirit/include/qi.hpp>
#include <boost/spirit/repository/include/qi_seek.hpp>



volatile int groupindex = 0;

enum BrowserType
{
    FIREFOX = 0 ,
    CHROME,
    SAFARI,
    OPERA,
    IE,
    EDGE,
    OTHER,
};

struct browser_type_sym : boost::spirit::qi::symbols<char, BrowserType> {
    browser_type_sym() {
        this->add
            ("Firefox", FIREFOX)
            ("Chrome",  CHROME)
            ("Safari",  SAFARI)
            ("Opera",   OPERA)
            ("MSIE",    IE)
            ("Edge",    EDGE)
            ("Trident", OTHER);
    }
} static const browser_type;

template <typename Types>
bool extract_browser_ids(std::string const& userAgent, Types& into) {
    using boost::spirit::repository::qi::seek;
    return parse(userAgent.begin(), userAgent.end(), *seek [ browser_type ], into);
}

const boost::regex BROWSERS_REGEX("(Firefox)|(Chrome)|(Safari)|(Opera)|(MSIE)|(Edge)|(Trident)");

int test_vector() {
    std::string const input("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Safari/537.36 Chrome/62.0.3202.94");
    std::vector<BrowserType> types;
    extract_browser_ids(input, types);
    for(auto type : types)
    {
	groupindex = type;
    }
   return 0;
}



int test_regex()
{
        // I expect two matches here CHROME and SAFARI
        std::string input("Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Safari/537.36 Chrome/62.0.3202.94");
        boost::sregex_iterator res(input.begin(), input.end(), BROWSERS_REGEX);
        boost::sregex_iterator end;
        for(; res != end; ++res)
        {
                // elude copy here ?
                boost::smatch what = *res;
                // Can I know the index of the matching group w/o 'for'?
                for (int type = 0;type < OTHER;type++)
                {
                        if (what[type+1].matched)
			{
				groupindex = type;
			}
                }

        }

        return 0;
}

void test_non_boost()
{
	const char *input = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Safari/537.36 Chrome/62.0.3202.94";
	const char *browsers[7] = {"Firefox", "Chrome", "Safari", "Opera", "MSIE", "Edge", "Trident"};
	int i = 0;
	for (const char **browser = &browsers[0];browser <= &browsers[6];browser++, i++)
	{
		if (strstr(input, *browser))
		{
			groupindex = i;
		}
	}
}

void test_isalpha()
{
    const char *input = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Safari/537.36 Chrome/62.0.3202.94";
    const char *browsers[OTHER+1] = {"Firefox", "Chrome", "Safari", "Opera", "MSIE", "Edge", "Trident"};
    const size_t browsers_len[OTHER+1] = {7, 5, 6, 5, 4, 4, 6};
    bool isFirstLetter = true;
	size_t _minSize = 4;
	size_t length = 0;
	for (const char *i = &input[0] ; *i != 0; ++i)
	{
		//If alpha its may be part of token
		if(isalpha(*i))
		{
			//Mark beginning of token
			if(isFirstLetter)
			{
				isFirstLetter = false;
				//Mark position in string
			}

			++length;
		}
		else
		{
			if(length >= _minSize)
			{
				//compare
				for(size_t j = 0; j < (OTHER+1) ; ++j)
				{
					if(browsers_len[j] == length && strncmp (browsers[j], i,length) == 0)
					{
						groupindex = j;
					}
				}
			}
			length = 0;
			isFirstLetter = true;
		}
	}

}


int main()
{
	for (int i =0;i < 500*1000;i++)
	{
//		test_vector();
	}
	for (int i =0;i < 500*1000;i++)
	{
//		test_regex();
	}

        for (int i =0;i < 500*1000;i++)
        {
//                test_non_boost();
        }


        for (int i =0;i < 500*1000;i++)
        {
              test_isalpha();
        }

}