Parse (split) a string in C++ using string delimiter (standard C++)

Question

I am parsing a string in C++ using the following:

using namespace std;

string parsed,input=\"text to be parsed\";
stringstream input_stringstream(input);

i         


        

Answer 1

Answer is already there, but selected-answer uses erase function which is very costly, think of some very big string(in MBs). Therefore I use below function.

vector<string> split(const string& i_str, const string& i_delim)
{
    vector<string> result;
    
    size_t found = i_str.find(i_delim);
    size_t startIndex = 0;

    while(found != string::npos)
    {
        result.push_back(string(i_str.begin()+startIndex, i_str.begin()+found));
        startIndex = found + i_delim.size();
        found = i_str.find(i_delim, startIndex);
    }
    if(startIndex != i_str.size())
        result.push_back(string(i_str.begin()+startIndex, i_str.end()));
    return result;      
}

Answer 2

This method uses std::string::find without mutating the original string by remembering the beginning and end of the previous substring token.

#include <iostream>
#include <string>

int main()
{
    std::string s = "scott>=tiger";
    std::string delim = ">=";

    auto start = 0U;
    auto end = s.find(delim);
    while (end != std::string::npos)
    {
        std::cout << s.substr(start, end - start) << std::endl;
        start = end + delim.length();
        end = s.find(delim, start);
    }

    std::cout << s.substr(start, end);
}

Answer 3

Here's my take on this. It handles the edge cases and takes an optional parameter to remove empty entries from the results.

bool endsWith(const std::string& s, const std::string& suffix)
{
    return s.size() >= suffix.size() &&
           s.substr(s.size() - suffix.size()) == suffix;
}

std::vector<std::string> split(const std::string& s, const std::string& delimiter, const bool& removeEmptyEntries = false)
{
    std::vector<std::string> tokens;

    for (size_t start = 0, end; start < s.length(); start = end + delimiter.length())
    {
         size_t position = s.find(delimiter, start);
         end = position != string::npos ? position : s.length();

         std::string token = s.substr(start, end - start);
         if (!removeEmptyEntries || !token.empty())
         {
             tokens.push_back(token);
         }
    }

    if (!removeEmptyEntries &&
        (s.empty() || endsWith(s, delimiter)))
    {
        tokens.push_back("");
    }

    return tokens;
}

Examples

split("a-b-c", "-"); // [3]("a","b","c")

split("a--c", "-"); // [3]("a","","c")

split("-b-", "-"); // [3]("","b","")

split("--c--", "-"); // [5]("","","c","","")

split("--c--", "-", true); // [1]("c")

split("a", "-"); // [1]("a")

split("", "-"); // [1]("")

split("", "-", true); // [0]()

Answer 4

Function:

std::vector<std::string> WSJCppCore::split(const std::string& sWhat, const std::string& sDelim) {
    std::vector<std::string> vRet;
    size_t nPos = 0;
    size_t nLen = sWhat.length();
    size_t nDelimLen = sDelim.length();
    while (nPos < nLen) {
        std::size_t nFoundPos = sWhat.find(sDelim, nPos);
        if (nFoundPos != std::string::npos) {
            std::string sToken = sWhat.substr(nPos, nFoundPos - nPos);
            vRet.push_back(sToken);
            nPos = nFoundPos + nDelimLen;
            if (nFoundPos + nDelimLen == nLen) { // last delimiter
                vRet.push_back("");
            }
        } else {
            std::string sToken = sWhat.substr(nPos, nLen - nPos);
            vRet.push_back(sToken);
            break;
        }
    }
    return vRet;
}

Unit-tests:

bool UnitTestSplit::run() {
bool bTestSuccess = true;

    struct LTest {
        LTest(
            const std::string &sStr,
            const std::string &sDelim,
            const std::vector<std::string> &vExpectedVector
        ) {
            this->sStr = sStr;
            this->sDelim = sDelim;
            this->vExpectedVector = vExpectedVector;
        };
        std::string sStr;
        std::string sDelim;
        std::vector<std::string> vExpectedVector;
    };
    std::vector<LTest> tests;
    tests.push_back(LTest("1 2 3 4 5", " ", {"1", "2", "3", "4", "5"}));
    tests.push_back(LTest("|1f|2п|3%^|44354|5kdasjfdre|2", "|", {"", "1f", "2п", "3%^", "44354", "5kdasjfdre", "2"}));
    tests.push_back(LTest("|1f|2п|3%^|44354|5kdasjfdre|", "|", {"", "1f", "2п", "3%^", "44354", "5kdasjfdre", ""}));
    tests.push_back(LTest("some1 => some2 => some3", "=>", {"some1 ", " some2 ", " some3"}));
    tests.push_back(LTest("some1 => some2 => some3 =>", "=>", {"some1 ", " some2 ", " some3 ", ""}));

    for (int i = 0; i < tests.size(); i++) {
        LTest test = tests[i];
        std::string sPrefix = "test" + std::to_string(i) + "(\"" + test.sStr + "\")";
        std::vector<std::string> vSplitted = WSJCppCore::split(test.sStr, test.sDelim);
        compareN(bTestSuccess, sPrefix + ": size", vSplitted.size(), test.vExpectedVector.size());
        int nMin = std::min(vSplitted.size(), test.vExpectedVector.size());
        for (int n = 0; n < nMin; n++) {
            compareS(bTestSuccess, sPrefix + ", element: " + std::to_string(n), vSplitted[n], test.vExpectedVector[n]);
        }
    }

    return bTestSuccess;
}

Answer 5

You can also use regex for this:

std::vector<std::string> split(const std::string str, const std::string regex_str)
{
    std::regex regexz(regex_str);
    std::vector<std::string> list(std::sregex_token_iterator(str.begin(), str.end(), regexz, -1),
                                  std::sregex_token_iterator());
    return list;
}

which is equivalent to :

std::vector<std::string> split(const std::string str, const std::string regex_str)
{
    std::sregex_token_iterator token_iter(str.begin(), str.end(), regexz, -1);
    std::sregex_token_iterator end;
    std::vector<std::string> list;
    while (token_iter != end)
    {
        list.emplace_back(*token_iter++);
    }
    return list;
}

and use it like this :

#include <iostream>
#include <string>
#include <regex>

std::vector<std::string> split(const std::string str, const std::string regex_str)
{   // a yet more concise form!
    return { std::sregex_token_iterator(str.begin(), str.end(), std::regex(regex_str), -1), std::sregex_token_iterator() };
}

int main()
{
    std::string input_str = "lets split this";
    std::string regex_str = " "; 
    auto tokens = split(input_str, regex_str);
    for (auto& item: tokens)
    {
        std::cout<<item <<std::endl;
    }
}

play with it online! http://cpp.sh/9sumb

you can simply use substrings, characters,etc like normal, or use actual regular experssions to do the splitting.
its also concize and C++11!

Answer 6

A very simple/naive approach:

vector<string> words_seperate(string s){
    vector<string> ans;
    string w="";
    for(auto i:s){
        if(i==' '){
           ans.push_back(w);
           w="";
        }
        else{
           w+=i;
        }
    }
    ans.push_back(w);
    return ans;
}

Or you can use boost library split function:

vector<string> result; 
boost::split(result, input, boost::is_any_of("\t"));

Or You can try TOKEN or strtok:

char str[] = "DELIMIT-ME-C++"; 
char *token = strtok(str, "-"); 
while (token) 
{ 
    cout<<token; 
    token = strtok(NULL, "-"); 
} 

Or You can do this:

char split_with=' ';
vector<string> words;
string token; 
stringstream ss(our_string);
while(getline(ss , token , split_with)) words.push_back(token);