Created
April 11, 2018 14:23
-
-
Save WANG-lp/bef46ff6ecb8ca235627763b9b863a75 to your computer and use it in GitHub Desktop.
qt stl boost string split performance comparation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <iostream> | |
#include <sstream> | |
#include <vector> | |
#include <string> | |
#include <random> | |
#include <ctime> | |
#include <chrono> | |
#include <cassert> | |
#include <QString> | |
#include <QStringList> | |
#include <boost/algorithm/string.hpp> | |
int boost_string_tokenizer(const char *raw_str){ | |
std::string str(raw_str); | |
typedef std::vector<std::string > split_vector_type; | |
split_vector_type SplitVec; // | |
boost::split( SplitVec, str, boost::is_any_of(","), boost::token_compress_off ); | |
return SplitVec.size(); | |
} | |
int stl_string_tokenizer(const char *raw_str){ | |
std::string str(raw_str); | |
std::istringstream split(str); | |
std::list<std::string> tokens; | |
for (std::string each; std::getline(split, each, ',');){ | |
tokens.push_back(std::move(each)); | |
} | |
return tokens.size(); | |
} | |
int qt_string_tokenizer(const char* raw_str){ | |
QString str(raw_str); | |
QStringList strList = str.split(','); | |
return strList.size(); | |
} | |
static const std::string base64_chars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; | |
using ns = std::chrono::nanoseconds; | |
using ms = std::chrono::milliseconds; | |
void benchmark_string_tokenizer(int number_of_test_cases, int max_number_of_words){ | |
std::vector<std::string> string_poll; | |
std::vector<int> string_number_of_works; | |
std::random_device rd; //Will be used to obtain a seed for the random number engine | |
std::mt19937 gen(rd()); //Standard mersenne_twister_engine seeded with rd() | |
std::uniform_int_distribution<> dis(1, max_number_of_words); // words for each sentence | |
std::uniform_int_distribution<> chars(0, 15); // char in base64 chars | |
std::uniform_int_distribution<> seg_len_gen(1, 100); // words for each sentence | |
std::cout << "start generate test data..." << std::endl; | |
for(int i = 0; i < number_of_test_cases; i++){ | |
int number_of_words = dis(gen); | |
std::cout << "gen data cases " << i << " with number of words " << number_of_words << std::endl; | |
std::stringstream ss; | |
for(int j = 0; j < number_of_words; j++){ | |
int segment_length = seg_len_gen(gen); | |
for(int k = 0; k < segment_length; k++){ | |
ss << base64_chars[chars(gen)]; | |
} | |
if(j < number_of_words -1){ | |
ss << ','; | |
} | |
} | |
std::string tmp_str = ss.str(); | |
string_poll.push_back(tmp_str); | |
string_number_of_works.push_back(number_of_words); | |
} | |
std::cout << "start testing stl library:" << std::endl; | |
auto startcputime = std::chrono::high_resolution_clock::now(); | |
for(int i = 0 ; i < number_of_test_cases; i++){ | |
assert(string_number_of_works[i] == stl_string_tokenizer(string_poll[i].c_str())); | |
} | |
auto endcputime = std::chrono::high_resolution_clock::now(); | |
std::cout<<"Elapsed time is : "<< std::chrono::duration_cast<ms>(endcputime - startcputime).count()<<" ms"<<std::endl; | |
std::cout << "start testing qt library:" << std::endl; | |
startcputime = std::chrono::high_resolution_clock::now(); | |
for(int i = 0 ; i < number_of_test_cases; i++){ | |
assert(string_number_of_works[i] == qt_string_tokenizer(string_poll[i].c_str())); | |
} | |
endcputime = std::chrono::high_resolution_clock::now(); | |
std::cout<<"Elapsed time is : "<< std::chrono::duration_cast<ms>(endcputime - startcputime).count()<<" ms"<<std::endl; | |
std::cout << "start testing boost library:" << std::endl; | |
startcputime = std::chrono::high_resolution_clock::now(); | |
for(int i = 0 ; i < number_of_test_cases; i++){ | |
assert(string_number_of_works[i] == boost_string_tokenizer(string_poll[i].c_str())); | |
} | |
endcputime = std::chrono::high_resolution_clock::now(); | |
std::cout<<"Elapsed time is : "<< std::chrono::duration_cast<ms>(endcputime - startcputime).count()<<" ms"<<std::endl; | |
} | |
int main() { | |
std::cout << stl_string_tokenizer("hello,world,there") << std::endl; | |
std::cout << qt_string_tokenizer("hello,world,there") << std::endl; | |
std::cout << boost_string_tokenizer("hello,world,there") << std::endl; | |
benchmark_string_tokenizer(1000, 10000); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
using following CMakeLists.txt file to compile above code: