fork download
copy 
  1. #include <algorithm>
  2. #include <cstring>
  3. #include <iostream>
  4. #include <iterator>
  5. #include <memory>
  6. #include <sstream>
  7. #include <string>
  8. #include <vector>
  9.  
  10. #include <boost/algorithm/string/classification.hpp>
  11. #include <boost/algorithm/string/split.hpp>
  12. #include <boost/tokenizer.hpp>
  13.  
  14. char* FindToken(
  15.     char* str, const char* delim, char** saveptr)
  16. {
  17. #if (_SVID_SOURCE || _BSD_SOURCE || _POSIX_C_SOURCE >= 1 || _XOPEN_SOURCE || _POSIX_SOURCE)
  18.     return ::strtok_r(str, delim, saveptr);
  19. #elif defined(_MSC_VER) && (_MSC_VER >= 1800)
  20.     return strtok_s(token, delim, saveptr);
  21. #else
  22.     return std::strtok(token, delim);
  23. #endif
  24. }
  25.  
  26. wchar_t* FindToken(
  27.     wchar_t* token, const wchar_t* delim, wchar_t** saveptr)
  28. {
  29. #if ( (defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L)) \
  30.   || (defined(__cplusplus) && (__cplusplus >= 201103L)) )
  31.     return std::wcstok(token, delim, saveptr);
  32. #elif defined(_MSC_VER) && (_MSC_VER >= 1800)
  33.     return wcstok_s(token, delim, saveptr);
  34. #else
  35.     return std::wcstok(token, delim);
  36. #endif
  37. }
  38.  
  39. char* CopyString(char* destination, const char* source)
  40. {
  41.     return std::strcpy(destination, source);
  42. }
  43.  
  44. wchar_t* CopyString(wchar_t* destination, const wchar_t* source)
  45. {
  46.     return std::wcscpy(destination, source);
  47. }
  48.  
  49. template <class charType>
  50. size_t splitWithFindToken(
  51.     const std::basic_string<charType>& str,
  52.     const std::basic_string<charType>& delim,
  53.     std::vector< std::basic_string<charType> >& tokens)
  54. {
  55.     std::unique_ptr<charType[]> ptr = std::make_unique<charType[]>(str.length() + 1);
  56.     memset(ptr.get(), 0, (str.length() + 1) * sizeof(charType));
  57.     CopyString(ptr.get(), str.c_str());
  58.     charType* saveptr;
  59.     charType* token = FindToken(ptr.get(), delim.c_str(), &saveptr);
  60.     while (token != nullptr)
  61.     {
  62.         tokens.push_back(token);
  63.         token = FindToken(nullptr, delim.c_str(), &saveptr);
  64.     }
  65.     return tokens.size();
  66. }
  67.  
  68. template <class charType>
  69. size_t splitWithStringStream(
  70.     const std::basic_string<charType>& str,
  71.     std::vector< std::basic_string<charType> >& tokens)
  72. {
  73.     typedef std::basic_string<charType> my_string;
  74.     typedef std::vector< std::basic_string<charType> > my_vector;
  75.     typedef std::basic_istringstream<
  76.         charType, std::char_traits<charType> >
  77.         my_istringstream;
  78.     typedef std::istream_iterator<
  79.         std::basic_string<charType>, charType,
  80.         std::char_traits<charType> >
  81.         my_istream_iterator;
  82.     tokens.clear();
  83.     if (str.empty())
  84.     {
  85.         return 0;
  86.     }
  87.     my_istringstream iss(str);
  88.     std::copy(
  89.         my_istream_iterator{iss}, my_istream_iterator(),
  90.         std::back_inserter<my_vector>(tokens));
  91.     return tokens.size();
  92. }
  93.  
  94. template <class charType>
  95. size_t splitWithStringStream1(
  96.     const std::basic_string<charType>& str,
  97.     std::vector< std::basic_string<charType> >& tokens)
  98. {
  99.     typedef std::basic_string<charType> my_string;
  100.     typedef std::vector< std::basic_string<charType> > my_vector;
  101.     typedef std::basic_istringstream<
  102.         charType, std::char_traits<charType> >
  103.         my_istringstream;
  104.     typedef std::istream_iterator<
  105.         std::basic_string<charType>, charType,
  106.         std::char_traits<charType> >
  107.         my_istream_iterator;
  108.     tokens.clear();
  109.     if (str.empty())
  110.     {
  111.         return 0;
  112.     }
  113.     my_istringstream iss(str);
  114. 	std::vector<my_string> results(
  115. 		my_istream_iterator{iss}, my_istream_iterator());
  116. 	tokens.swap(results);
  117.     return tokens.size();
  118. }
  119.  
  120. template<typename charType>
  121. size_t splitWithGetLine(
  122.     const std::basic_string<charType>& str,
  123.     const charType delim,
  124.     std::vector< std::basic_string<charType> >& tokens)
  125. {
  126.     typedef std::basic_string<charType> my_string;
  127.     typedef std::basic_istringstream<
  128.         charType, std::char_traits<charType> >
  129.         my_istringstream;
  130.     tokens.clear();
  131.     if (str.empty())
  132.     {
  133.        return 0;
  134.     }
  135.     my_istringstream iss(str);
  136.     my_string token;
  137.     while (std::getline(iss, token, delim))
  138.     {
  139.         tokens.push_back(token);
  140.     }
  141.     return tokens.size();
  142. }
  143.  
  144. template<typename charType>
  145. size_t splitWithBasicString(
  146.     const std::basic_string<charType>& str,
  147.     const charType delim,
  148.     std::vector< std::basic_string<charType> > &tokens,
  149.     const bool trimEmpty = false,
  150.     const size_t maxTokens = (size_t)(-1))
  151. {
  152.     typedef std::basic_string<charType> my_string;
  153.     typedef typename my_string::size_type my_size_type;
  154.     tokens.clear();
  155.     if (str.empty())
  156.     {
  157.         return 0;
  158.     }
  159.     my_size_type len = str.length();
  160.     // Skip delimiters at beginning.
  161.     my_size_type left = str.find_first_not_of(delim, 0);
  162.     size_t i = 1;
  163.     if (!trimEmpty && left != 0)
  164.     {
  165.         tokens.push_back(my_string());
  166.         ++i;
  167.     }
  168.     while (i < maxTokens)
  169.     {
  170.         my_size_type right = str.find(delim, left);
  171.         if (right == my_string::npos)
  172.         {
  173.             break;
  174.         }
  175.         if (!trimEmpty || right - left > 0)
  176.         {
  177.             tokens.push_back(str.substr(left, right - left));
  178.             ++i;
  179.         }
  180.         left = right + 1;
  181.     }
  182.     if (left < len)
  183.     {
  184.         tokens.push_back(str.substr(left));
  185.     }
  186.     return tokens.size();
  187. }
  188.  
  189. template<typename charType>
  190. size_t splitWithBasicString(
  191.     const std::basic_string<charType>& str,
  192.     const std::basic_string<charType>& delim,
  193.     std::vector< std::basic_string<charType> >& tokens,
  194.     const bool trimEmpty = false,
  195.     const size_t maxTokens = (size_t)(-1))
  196. {
  197.     typedef std::basic_string<charType> my_string;
  198.     typedef typename my_string::size_type my_size_type;
  199.     tokens.clear();
  200.     if (str.empty())
  201.     {
  202.        return 0;
  203.     }
  204.     my_size_type len = str.length();
  205.     // Skip delimiters at beginning.
  206.     my_size_type left = str.find_first_not_of(delim, 0);
  207.     size_t i = 1;
  208.     if (!trimEmpty && left != 0)
  209.     {
  210.         tokens.push_back(my_string());
  211.         ++i;
  212.     }
  213.     while (i < maxTokens)
  214.     {
  215.         my_size_type right = str.find_first_of(delim, left);
  216.         if (right == my_string::npos)
  217.         {
  218.            break;
  219.         }
  220.         if (!trimEmpty || right - left > 0)
  221.         {
  222.             tokens.push_back(str.substr(left, right - left));
  223.             ++i;
  224.         }
  225.         left = right + 1;
  226.     }
  227.     if (left < len)
  228.     {
  229.        tokens.push_back(str.substr(left));
  230.     }
  231.     return tokens.size();
  232. }
  233.  
  234. int main()
  235. {
  236.     std::wstring str(L"The quick brown fox jumped over the lazy dog.");
  237.     std::wstring str1(L"This is a test.||This is only a test.|This concludes this test.");
  238.     std::wstring str2(L"This is a test.|,This is only a test.\tThis concludes this test.");
  239.     std::vector<std::wstring> tokens;
  240.     size_t s = splitWithStringStream(str, tokens);
  241.     std::wcout << L"s: " << s << std::endl;
  242.     if (s)
  243.     {
  244.         std::wcout
  245.             << L"tokens.at(0): " << tokens.at(0)
  246.             << std::endl;
  247.     }
  248.     std::vector<std::wstring> tokens1;
  249.     size_t s1 = splitWithStringStream1(str, tokens1);
  250.     std::wcout << L"s1: " << s1 << std::endl;
  251.     if (s1)
  252.     {
  253.         std::wcout
  254.             << L"tokens1.at(0): " << tokens1.at(0)
  255.             << std::endl;
  256.     }
  257.     std::vector<std::wstring> tokens2;
  258.     size_t s2 = splitWithGetLine(str1, L'|', tokens2);
  259.     std::wcout << L"s2: " << s2 << std::endl;
  260.     if (s2)
  261.     {
  262.         std::wcout
  263.             << L"tokens2.at(0): " << tokens2.at(0)
  264.             << std::endl;
  265.     }
  266.     std::vector<std::wstring> tokens3;
  267.     size_t s3 = splitWithBasicString(str1, L'|', tokens3, true);
  268.     std::wcout << L"s3: " << s3 << std::endl;
  269.     if (s3)
  270.     {
  271.         std::wcout
  272.             << L"tokens3.at(0): " << tokens3.at(0)
  273.             << std::endl;
  274.     }
  275.     std::vector<std::wstring> tokens4;
  276.     size_t s4 = splitWithBasicString(
  277.         str2, std::wstring(L"|,\t"), tokens4, true);
  278.     std::wcout << L"s4: " << s4 << std::endl;
  279.     if (s4)
  280.     {
  281.         std::wcout
  282.             << L"tokens4.at(0): " << tokens4.at(0)
  283.             << std::endl;
  284.     }
  285.     std::vector<std::wstring> tokens5;
  286.     boost::split(tokens5, str2, boost::is_any_of(L"|,\t"));
  287.     size_t s5 = tokens5.size();
  288.     std::wcout << L"s5: " << s5 << std::endl;
  289.     if (s5)
  290.     {
  291.         std::wcout
  292.             << L"tokens5.at(0): " << tokens5.at(0)
  293.             << std::endl;
  294.     }
  295.     std::vector<std::wstring> tokens6;
  296.     size_t s6 = splitWithFindToken(
  297.         str2, std::wstring(L"|,\t"), tokens6);
  298.     std::wcout << L"s6: " << s6 << std::endl;
  299.     if (s6)
  300.     {
  301.         std::wcout
  302.             << L"tokens6.at(0): " << tokens6.at(0)
  303.             << std::endl;
  304.     }
  305.     typedef boost::char_separator<wchar_t> my_separator;
  306.     typedef boost::tokenizer<
  307.         my_separator, std::wstring::const_iterator,
  308.         std::wstring > my_tokenizer;
  309.     my_separator sep(L"|,\t");
  310.     my_tokenizer tokens7(str2, sep);
  311.     my_tokenizer::iterator itEnd = tokens7.end();
  312.     for (my_tokenizer::iterator it = tokens7.begin(); it != itEnd; ++it)
  313.     {
  314.         std::wcout << *it << std::endl;
  315.     }
  316. 	return 0;
  317. }
  318.  
Success #stdin #stdout 0s 15272KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
s: 9
tokens.at(0): The
s1: 9
tokens1.at(0): The
s2: 4
tokens2.at(0): This is a test.
s3: 3
tokens3.at(0): This is a test.
s4: 3
tokens4.at(0): This is a test.
s5: 4
tokens5.at(0): This is a test.
s6: 3
tokens6.at(0): This is a test.
This is a test.
This is only a test.
This concludes this test.
https://ideone.com/OqV09t
Splitting a string in C++
language:
C++14 (gcc 8.3)
created:
6 years ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!