What is the right way to split a string into a vector of strings? Delimiter is space or comma.
211 Answers
A convenient way would be boost's string algorithms library.
#include <boost/algorithm/string/classification.hpp> // Include boost::for is_any_of #include <boost/algorithm/string/split.hpp> // Include for boost::split // ... std::vector<std::string> words; std::string s; boost::split(words, s, boost::is_any_of(", "), boost::token_compress_on); For space separated strings, then you can do this:
std::string s = "What is the right way to split a string into a vector of strings"; std::stringstream ss(s); std::istream_iterator<std::string> begin(ss); std::istream_iterator<std::string> end; std::vector<std::string> vstrings(begin, end); std::copy(vstrings.begin(), vstrings.end(), std::ostream_iterator<std::string>(std::cout, "\n")); Output:
What is the right way to split a string into a vector of strings string that have both comma and space
struct tokens: std::ctype<char> { tokens(): std::ctype<char>(get_table()) {} static std::ctype_base::mask const* get_table() { typedef std::ctype<char> cctype; static const cctype::mask *const_rc= cctype::classic_table(); static cctype::mask rc[cctype::table_size]; std::memcpy(rc, const_rc, cctype::table_size * sizeof(cctype::mask)); rc[','] = std::ctype_base::space; rc[' '] = std::ctype_base::space; return &rc[0]; } }; std::string s = "right way, wrong way, correct way"; std::stringstream ss(s); ss.imbue(std::locale(std::locale(), new tokens())); std::istream_iterator<std::string> begin(ss); std::istream_iterator<std::string> end; std::vector<std::string> vstrings(begin, end); std::copy(vstrings.begin(), vstrings.end(), std::ostream_iterator<std::string>(std::cout, "\n")); Output:
right way wrong way correct way You can use getline with delimiter:
string s, tmp; stringstream ss(s); vector<string> words; while(getline(ss, tmp, ',')){ words.push_back(tmp); ..... } vector<string> split(string str, string token){ vector<string>result; while(str.size()){ int index = str.find(token); if(index!=string::npos){ result.push_back(str.substr(0,index)); str = str.substr(index+token.size()); if(str.size()==0)result.push_back(str); }else{ result.push_back(str); str = ""; } } return result; } 1split("1,2,3",",") ==> ["1","2","3"]
split("1,2,",",") ==> ["1","2",""]
split("1token2token3","token") ==> ["1","2","3"]
If the string has both spaces and commas you can use the string class function
found_index = myString.find_first_of(delims_str, begin_index) in a loop. Checking for != npos and inserting into a vector. If you prefer old school you can also use C's
strtok() method.
std::vector<std::string> split(std::string text, char delim) { std::string line; std::vector<std::string> vec; std::stringstream ss(text); while(std::getline(ss, line, delim)) { vec.push_back(line); } return vec; } split("String will be split", ' ') -> {"String", "will", "be", "split"}
split("Hello, how are you?", ',') -> {"Hello", "how are you?"}
EDIT: Here's a thing I made, this can use multi-char delimiters, albeit I'm not 100% sure if it always works:
std::vector<std::string> split(std::string text, std::string delim) { std::vector<std::string> vec; size_t pos = 0, prevPos = 0; while (1) { pos = text.find(delim, prevPos); if (pos == std::string::npos) { vec.push_back(text.substr(prevPos)); return vec; } vec.push_back(text.substr(prevPos, pos - prevPos)); prevPos = pos + delim.length(); } } Tweaked version from Techie Delight:
#include <string> #include <vector> std::vector<std::string> split(const std::string& str, char delim) { std::vector<std::string> strings; size_t start; size_t end = 0; while ((start = str.find_first_not_of(delim, end)) != std::string::npos) { end = str.find(delim, start); strings.push_back(str.substr(start, end - start)); } return strings; } i made this custom function that will convert the line to vector
#include <iostream> #include <vector> #include <ctime> #include <string> using namespace std; int main(){ string line; getline(cin, line); int len = line.length(); vector<string> subArray; for (int j = 0, k = 0; j < len; j++) { if (line[j] == ' ') { string ch = line.substr(k, j - k); k = j+1; subArray.push_back(ch); } if (j == len - 1) { string ch = line.substr(k, j - k+1); subArray.push_back(ch); } } return 0; } Here is a modified version of roach's solution that splits based on a string of single character delimiters + supports the option to compress duplicate delimiters.
std::vector<std::string> split(std::string text, std::string delim, bool compress) { std::vector<std::string> vec; size_t pos = 0, prevPos = 0; while (1) { pos = text.find_first_of(delim, prevPos); while(compress) { if( prevPos == pos ) prevPos++; else break; pos = text.find_first_of(delim, prevPos); } if (pos == std::string::npos) { if(prevPos != text.size()) vec.push_back(text.substr(prevPos)); return vec; } vec.push_back(text.substr(prevPos, pos - prevPos)); prevPos = pos + 1; } } Example without compress:
std::string s = " 1.2 foo@foo . "; auto res = split(s, ".@ ", false); for(auto i : res) std::cout << "string {" << i << "}" << std::endl; Output:
string {} string {} string {1} string {2} string {} string {foo} string {foo} string {} string {} With compress split(s, ".@ ", true);
string {1} string {2} string {foo} string {foo} Here's a function that will split up a string into a vector but it doesn't include empty strings in the output vector.
vector<string> split(string str, string token) { vector<string> result; while (str.size()) { int index = str.find(token); string substr; if ((substr = str.substr(0, index)) == "") { str = str.substr(index + token.size()); } else if (index != string::npos) { result.push_back(substr); str = str.substr(index + token.size()); } else { result.push_back(str); str = ""; } } return result; } Note: The above was adapted from this answer.
Usage
void test() { string a = "hello : world : ok : fine"; auto r = split(a, " : ", 2); for (auto e: r) { cout << e << endl; } } static inline std::vector<std::string> split(const std::string &str, const std::string &delimiter = " ", const int max_elements = 0) { std::vector<std::string> tokens; std::string::size_type start_index = 0; while (true) { std::string::size_type next_index = str.find(delimiter, start_index); if (next_index == std::string::npos) { tokens.push_back(str.substr(start_index)); break; } else { tokens.push_back(str.substr(start_index, next_index - start_index)); start_index = next_index + delimiter.length(); } if (max_elements > 0 && tokens.size() == max_elements - 1) { tokens.push_back(str.substr(start_index)); break; } } return tokens; } 
