[c++] Right way to split an std::string into a vector<string>

Possible Duplicate:
How to split a string?

What is the right way to split a string into a vector of strings. Delimiter is space or comma.

This question is related to c++ string

The answer is


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();
    }
}

You can use getline with delimiter:

string s, tmp; 
stringstream ss(s);
vector<string> words;

while(getline(ss, tmp, ',')){
    words.push_back(tmp);
    .....
}

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;
}

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.


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;
}

split("1,2,3",",") ==> ["1","2","3"]

split("1,2,",",") ==> ["1","2",""]

split("1token2token3","token") ==> ["1","2","3"]


I write this custom function this will help you. But make discussions about the Time complexity.

std::vector<std::string> words;
std::string s;
std::string separator = ",";

while(s.find(separator) != std::string::npos){
   separatorIndex = s.find(separator)
   vtags.push_back(s.substr(0, separatorIndex ));
   words= s.substr(separatorIndex + 1, s.length());
}

words.push_back(s);


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;
}

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);