Skip to content

Instantly share code, notes, and snippets.

@jdh30
Created May 9, 2019 10:19
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save jdh30/7fe500222d2f39519146d0da48f70493 to your computer and use it in GitHub Desktop.
Save jdh30/7fe500222d2f39519146d0da48f70493 to your computer and use it in GitHub Desktop.
Regular expression benchmark in C++
#include "stdafx.h"
#include <windows.h>
#include <regex>
#include <vector>
#include <string>
#include <fstream>
#include <cstdio>
#include <codecvt>
using namespace std;
wstring load(wstring filename) {
const locale empty_locale = locale::empty();
typedef codecvt_utf8<wchar_t> converter_type;
const converter_type* converter = new converter_type;
const locale utf8_locale = locale(empty_locale, converter);
wifstream in(filename);
wstring contents;
if (in)
{
in.seekg(0, ios::end);
contents.resize(in.tellg());
in.seekg(0, ios::beg);
in.read(&contents[0], contents.size());
in.close();
}
return(contents);
}
int count(const wstring &re, const wstring &s){
static const wregex rsplit(re);
auto rit = wsregex_token_iterator(s.begin(), s.end(), rsplit, -1);
auto rend = wsregex_token_iterator();
int count=0;
for (auto it=rit; it!=rend; ++it)
count += it->length();
return count;
}
int _tmain(int argc, _TCHAR* argv[])
{
wstring str = load(L"pg10.txt");
wstring re = load(L"re.txt");
__int64 freq, tStart, tStop;
unsigned long TimeDiff;
QueryPerformanceFrequency((LARGE_INTEGER *)&freq);
QueryPerformanceCounter((LARGE_INTEGER *)&tStart);
vector<int> res(4);
#pragma omp parallel num_threads(4)
for(auto i=0; i<res.size(); ++i)
res[i] = count(re, str);
QueryPerformanceCounter((LARGE_INTEGER *)&tStop);
TimeDiff = (unsigned long)(((tStop - tStart) * 1000000) / freq);
printf("(%d, %d, %d, %d) %fs\n", res[0], res[1], res[2], res[3], TimeDiff/1e6);
return 0;
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment