Related
I am parsing a string in C++ using the following:
using namespace std;
string parsed,input="text to be parsed";
stringstream input_stringstream(input);
if (getline(input_stringstream,parsed,' '))
{
// do some processing.
}
Parsing with a single char delimiter is fine. But what if I want to use a string as delimiter.
Example: I want to split:
scott>=tiger
with >= as delimiter so that I can get scott and tiger.
You can use the std::string::find() function to find the position of your string delimiter, then use std::string::substr() to get a token.
Example:
std::string s = "scott>=tiger";
std::string delimiter = ">=";
std::string token = s.substr(0, s.find(delimiter)); // token is "scott"
The find(const string& str, size_t pos = 0) function returns the position of the first occurrence of str in the string, or npos if the string is not found.
The substr(size_t pos = 0, size_t n = npos) function returns a substring of the object, starting at position pos and of length npos.
If you have multiple delimiters, after you have extracted one token, you can remove it (delimiter included) to proceed with subsequent extractions (if you want to preserve the original string, just use s = s.substr(pos + delimiter.length());):
s.erase(0, s.find(delimiter) + delimiter.length());
This way you can easily loop to get each token.
Complete Example
std::string s = "scott>=tiger>=mushroom";
std::string delimiter = ">=";
size_t pos = 0;
std::string token;
while ((pos = s.find(delimiter)) != std::string::npos) {
token = s.substr(0, pos);
std::cout << token << std::endl;
s.erase(0, pos + delimiter.length());
}
std::cout << s << std::endl;
Output:
scott
tiger
mushroom
For string delimiter
Split string based on a string delimiter. Such as splitting string "adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih" based on string delimiter "-+", output will be {"adsf", "qwret", "nvfkbdsj", "orthdfjgh", "dfjrleih"}
#include <iostream>
#include <sstream>
#include <vector>
// for string delimiter
std::vector<std::string> split(std::string s, std::string delimiter) {
size_t pos_start = 0, pos_end, delim_len = delimiter.length();
std::string token;
std::vector<std::string> res;
while ((pos_end = s.find(delimiter, pos_start)) != std::string::npos) {
token = s.substr (pos_start, pos_end - pos_start);
pos_start = pos_end + delim_len;
res.push_back (token);
}
res.push_back (s.substr (pos_start));
return res;
}
int main() {
std::string str = "adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih";
std::string delimiter = "-+";
std::vector<std::string> v = split (str, delimiter);
for (auto i : v) cout << i << endl;
return 0;
}
**Output**
adsf
qwret
nvfkbdsj
orthdfjgh
dfjrleih
For single character delimiter
Split string based on a character delimiter. For example, splitting string "adsf+qwer+poui+fdgh" with delimiter "+" will output {"adsf", "qwer", "poui", "fdgh"}
#include <iostream>
#include <sstream>
#include <vector>
std::vector<std::string> split (const std::string &s, char delim) {
std::vector<std::string> result;
std::stringstream ss (s);
std::string item;
while (getline (ss, item, delim)) {
result.push_back (item);
}
return result;
}
int main() {
std::string str = "adsf+qwer+poui+fdgh";
std::vector<std::string> v = split (str, '+');
for (auto i : v) cout << i << endl;
return 0;
}
**Output**
adsf
qwer
poui
fdgh
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);
}
You can use next function to split string:
vector<string> split(const string& str, const string& delim)
{
vector<string> tokens;
size_t prev = 0, pos = 0;
do
{
pos = str.find(delim, prev);
if (pos == string::npos) pos = str.length();
string token = str.substr(prev, pos-prev);
if (!token.empty()) tokens.push_back(token);
prev = pos + delim.length();
}
while (pos < str.length() && prev < str.length());
return tokens;
}
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) {
std::regex regexz(regex_str);
return {std::sregex_token_iterator(str.begin(), str.end(), regexz, -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!
you can simply use substrings, characters, etc like normal, or use actual regular expressions to do the splitting.
its also concise and C++11!
A way of doing it with C++20:
#include <iostream>
#include <ranges>
#include <string_view>
int main()
{
std::string hello = "text to be parsed";
auto split = hello
| std::ranges::views::split(' ')
| std::ranges::views::transform([](auto&& str) { return std::string_view(&*str.begin(), std::ranges::distance(str)); });
for (auto&& word : split)
{
std::cout << word << std::endl;
}
}
See:
https://stackoverflow.com/a/48403210/10771848
https://en.cppreference.com/w/cpp/ranges/split_view
This code splits lines from text, and add everyone into a vector.
vector<string> split(char *phrase, string delimiter){
vector<string> list;
string s = string(phrase);
size_t pos = 0;
string token;
while ((pos = s.find(delimiter)) != string::npos) {
token = s.substr(0, pos);
list.push_back(token);
s.erase(0, pos + delimiter.length());
}
list.push_back(s);
return list;
}
Called by:
vector<string> listFilesMax = split(buffer, "\n");
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 startIndex = 0;
for (size_t found = i_str.find(i_delim); found != string::npos; found = i_str.find(i_delim, startIndex))
{
result.emplace_back(i_str.begin()+startIndex, i_str.begin()+found);
startIndex = found + i_delim.size();
}
if (startIndex != i_str.size())
result.emplace_back(i_str.begin()+startIndex, i_str.end());
return result;
}
strtok allows you to pass in multiple chars as delimiters. I bet if you passed in ">=" your example string would be split correctly (even though the > and = are counted as individual delimiters).
EDIT if you don't want to use c_str() to convert from string to char*, you can use substr and find_first_of to tokenize.
string token, mystring("scott>=tiger");
while(token != mystring){
token = mystring.substr(0,mystring.find_first_of(">="));
mystring = mystring.substr(mystring.find_first_of(">=") + 1);
printf("%s ",token.c_str());
}
I would use boost::tokenizer. Here's documentation explaining how to make an appropriate tokenizer function: http://www.boost.org/doc/libs/1_52_0/libs/tokenizer/tokenizerfunction.htm
Here's one that works for your case.
struct my_tokenizer_func
{
template<typename It>
bool operator()(It& next, It end, std::string & tok)
{
if (next == end)
return false;
char const * del = ">=";
auto pos = std::search(next, end, del, del + 2);
tok.assign(next, pos);
next = pos;
if (next != end)
std::advance(next, 2);
return true;
}
void reset() {}
};
int main()
{
std::string to_be_parsed = "1) one>=2) two>=3) three>=4) four";
for (auto i : boost::tokenizer<my_tokenizer_func>(to_be_parsed))
std::cout << i << '\n';
}
This should work perfectly for string (or single character) delimiters. Don't forget to include #include <sstream>.
std::string input = "Alfa=,+Bravo=,+Charlie=,+Delta";
std::string delimiter = "=,+";
std::istringstream ss(input);
std::string token;
std::string::iterator it;
while(std::getline(ss, token, *(it = delimiter.begin()))) {
std::cout << token << std::endl; // Token is extracted using '='
it++;
// Skip the rest of delimiter if exists ",+"
while(it != delimiter.end() and ss.peek() == *(it)) {
it++; ss.get();
}
}
The first while loop extracts a token using the first character of the string delimiter. The second while loop skips the rest of the delimiter and stops at the beginning of the next token.
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 != std::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]()
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);
Just in case in the future, someone wants out of the box function of Vincenzo Pii 's answer
#include <vector>
#include <string>
std::vector<std::string> SplitString(
std::string str,
std::string delimeter)
{
std::vector<std::string> splittedStrings = {};
size_t pos = 0;
while ((pos = str.find(delimeter)) != std::string::npos)
{
std::string token = str.substr(0, pos);
if (token.length() > 0)
splittedStrings.push_back(token);
str.erase(0, pos + delimeter.length());
}
if (str.length() > 0)
splittedStrings.push_back(str);
return splittedStrings;
}
I also fixed some bugs so that the function won't return an empty string if there is a delimiter at the start or the end of the string
This is a complete method that splits the string on any delimiter and returns a vector of the chopped up strings.
It is an adaptation from the answer from ryanbwork. However, his check for: if(token != mystring) gives wrong results if you have repeating elements in your string. This is my solution to that problem.
vector<string> Split(string mystring, string delimiter)
{
vector<string> subStringList;
string token;
while (true)
{
size_t findfirst = mystring.find_first_of(delimiter);
if (findfirst == string::npos) //find_first_of returns npos if it couldn't find the delimiter anymore
{
subStringList.push_back(mystring); //push back the final piece of mystring
return subStringList;
}
token = mystring.substr(0, mystring.find_first_of(delimiter));
mystring = mystring.substr(mystring.find_first_of(delimiter) + 1);
subStringList.push_back(token);
}
return subStringList;
}
Since this is the top-rated Stack Overflow Google search result for C++ split string or similar, I'll post a complete, copy/paste runnable example that shows both methods.
splitString uses stringstream (probably the better and easier option in most cases)
splitString2 uses find and substr (a more manual approach)
// SplitString.cpp
#include <iostream>
#include <vector>
#include <string>
#include <sstream>
// function prototypes
std::vector<std::string> splitString(const std::string& str, char delim);
std::vector<std::string> splitString2(const std::string& str, char delim);
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx);
int main(void)
{
// Test cases - all will pass
std::string str = "ab,cd,ef";
//std::string str = "abcdef";
//std::string str = "";
//std::string str = ",cd,ef";
//std::string str = "ab,cd,"; // behavior of splitString and splitString2 is different for this final case only, if this case matters to you choose which one you need as applicable
std::vector<std::string> tokens = splitString(str, ',');
std::cout << "tokens: " << "\n";
if (tokens.empty())
{
std::cout << "(tokens is empty)" << "\n";
}
else
{
for (auto& token : tokens)
{
if (token == "") std::cout << "(empty string)" << "\n";
else std::cout << token << "\n";
}
}
return 0;
}
std::vector<std::string> splitString(const std::string& str, char delim)
{
std::vector<std::string> tokens;
if (str == "") return tokens;
std::string currentToken;
std::stringstream ss(str);
while (std::getline(ss, currentToken, delim))
{
tokens.push_back(currentToken);
}
return tokens;
}
std::vector<std::string> splitString2(const std::string& str, char delim)
{
std::vector<std::string> tokens;
if (str == "") return tokens;
int leftIdx = 0;
int delimIdx = str.find(delim);
int rightIdx;
while (delimIdx != std::string::npos)
{
rightIdx = delimIdx - 1;
std::string token = getSubstring(str, leftIdx, rightIdx);
tokens.push_back(token);
// prep for next time around
leftIdx = delimIdx + 1;
delimIdx = str.find(delim, delimIdx + 1);
}
rightIdx = str.size() - 1;
std::string token = getSubstring(str, leftIdx, rightIdx);
tokens.push_back(token);
return tokens;
}
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx)
{
return str.substr(leftIdx, rightIdx - leftIdx + 1);
}
Yet another answer: Here I'm using find_first_not_of string function which returns the position of the first character that does not match any of the characters specified in the delim.
size_t find_first_not_of(const string& delim, size_t pos = 0) const noexcept;
Example:
int main()
{
size_t start = 0, end = 0;
std::string str = "scott>=tiger>=cat";
std::string delim = ">=";
while ((start = str.find_first_not_of(delim, end)) != std::string::npos)
{
end = str.find(delim, start); // finds the 'first' occurance from the 'start'
std::cout << str.substr(start, end - start)<<std::endl; // extract substring
}
return 0;
}
Output:
scott
tiger
cat
I make this solution. It is very simple, all the prints/values are in the loop (no need to check after the loop).
#include <iostream>
#include <string>
using std::cout;
using std::string;
int main() {
string s = "it-+is-+working!";
string d = "-+";
int firstFindI = 0;
int secendFindI = 0;
while (secendFindI != string::npos)
{
secendFindI = s.find(d, firstFindI);
cout << s.substr(firstFindI, secendFindI - firstFindI) << "\n"; // print sliced part
firstFindI = secendFindI + d.size(); // add to the search index
}
}
Thanks to #SteveWard for improving this answer.
This is similar to other answers but it's using string_view. So these are just views for the original string. Similar to the c++20 example. Though this would be a c++17 example. (edit to skip empty matches)
#include <algorithm>
#include <iostream>
#include <string_view>
#include <vector>
std::vector<std::string_view> split(std::string_view buffer,
const std::string_view delimeter = " ") {
std::vector<std::string_view> ret{};
std::decay_t<decltype(std::string_view::npos)> pos{};
while ((pos = buffer.find(delimeter)) != std::string_view::npos) {
const auto match = buffer.substr(0, pos);
if (!match.empty()) ret.push_back(match);
buffer = buffer.substr(pos + delimeter.size());
}
if (!buffer.empty()) ret.push_back(buffer);
return ret;
}
int main() {
const auto split_values = split("1 2 3 4 5 6 7 8 9 10 ");
std::for_each(split_values.begin(), split_values.end(),
[](const auto& str) { std::cout << str << '\n'; });
return split_values.size();
}
If you do not want to modify the string (as in the answer by Vincenzo Pii) and want to output the last token as well, you may want to use this approach:
inline std::vector<std::string> splitString( const std::string &s, const std::string &delimiter ){
std::vector<std::string> ret;
size_t start = 0;
size_t end = 0;
size_t len = 0;
std::string token;
do{ end = s.find(delimiter,start);
len = end - start;
token = s.substr(start, len);
ret.emplace_back( token );
start += len + delimiter.length();
std::cout << token << std::endl;
}while ( end != std::string::npos );
return ret;
}
Here's a concise split function. I decided to have back to back delimiters return as an empty string but you could easily check that if the substring is empty and not add it to the vector if it is.
#include <vector>
#include <string>
using namespace std;
vector<string> split(string to_split, string delimiter) {
size_t pos = 0;
vector<string> matches{};
do {
pos = to_split.find(delimiter);
int change_end;
if (pos == string::npos) {
pos = to_split.length() - 1;
change_end = 1;
}
else {
change_end = 0;
}
matches.push_back(to_split.substr(0, pos+change_end));
to_split.erase(0, pos+1);
}
while (!to_split.empty());
return matches;
}
This method use string find and string substr
vector<string> split(const string& str,const string delim){
vector<string> vtokens;
size_t start = 0;
size_t end = 0;
while((end = str.find(delim,start))!=string::npos){
vtokens.push_back(str.substr(start,end-start));
start = end +1;
}
vtokens.push_back(str.substr(start));
return vtokens;
}
#include<iostream>
#include<algorithm>
using namespace std;
int split_count(string str,char delimit){
return count(str.begin(),str.end(),delimit);
}
void split(string str,char delimit,string res[]){
int a=0,i=0;
while(a<str.size()){
res[i]=str.substr(a,str.find(delimit));
a+=res[i].size()+1;
i++;
}
}
int main(){
string a="abc.xyz.mno.def";
int x=split_count(a,'.')+1;
string res[x];
split(a,'.',res);
for(int i=0;i<x;i++)
cout<<res[i]<<endl;
return 0;
}
P.S: Works only if the lengths of the strings after splitting are equal
std::vector<std::string> parse(std::string str,std::string delim){
std::vector<std::string> tokens;
char *str_c = strdup(str.c_str());
char* token = NULL;
token = strtok(str_c, delim.c_str());
while (token != NULL) {
tokens.push_back(std::string(token));
token = strtok(NULL, delim.c_str());
}
delete[] str_c;
return tokens;
}
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;
}
i use pointer arithmetic. inner while for string delimeter if you satify with char delim just remove inner while simply. i hope it is correct. if you notice any mistake or improve please leave the comment.
std::vector<std::string> split(std::string s, std::string delim)
{
char *p = &s[0];
char *d = &delim[0];
std::vector<std::string> res = {""};
do
{
bool is_delim = true;
char *pp = p;
char *dd = d;
while (*dd && is_delim == true)
if (*pp++ != *dd++)
is_delim = false;
if (is_delim)
{
p = pp - 1;
res.push_back("");
}
else
*(res.rbegin()) += *p;
} while (*p++);
return res;
}
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.push_back(std::forward<T>(t)), void()) {
c.push_back(std::forward<T>(t));
}
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.insert(std::forward<T>(t)), void()) {
c.insert(std::forward<T>(t));
}
template<typename Container>
Container splitR(const std::string& input, const std::string& delims) {
Container out;
size_t delims_len = delims.size();
auto begIdx = 0u;
auto endIdx = input.find(delims, begIdx);
if (endIdx == std::string::npos && input.size() != 0u) {
insert_in_container(out, input);
}
else {
size_t w = 0;
while (endIdx != std::string::npos) {
w = endIdx - begIdx;
if (w != 0) insert_in_container(out, input.substr(begIdx, w));
begIdx = endIdx + delims_len;
endIdx = input.find(delims, begIdx);
}
w = input.length() - begIdx;
if (w != 0) insert_in_container(out, input.substr(begIdx, w));
}
return out;
}
A simpler solution would be -
You can use strtok to delimit on the basis of multichar delimiter.
Remember to use strdup so that the orignal string isn't mutated.
#include <stdio.h>
#include <string.h>
const char* str = "scott>=tiger";
char *token = strtok(strdup(str), ">=");
while (token != NULL)
{
printf("%s\n", token);
token = strtok(NULL, ">=");
}
I looked through the answers and haven't seen an iterator based approach that can be fed into a range loop, so I made one.
This uses C++17 string_views so it shouldn't allocate copies of the string.
struct StringSplit
{
struct Iterator
{
size_t tokenStart_ = 0;
size_t tokenEnd_ = 0;
std::string str_;
std::string_view view_;
std::string delimiter_;
bool done_ = false;
Iterator()
{
// End iterator.
done_ = true;
}
Iterator(std::string str, std::string delimiter)
: str_{std::move(str)}, view_{str_}, delimiter_{
std::move(delimiter)}
{
tokenEnd_ = view_.find(delimiter_, tokenStart_);
}
std::string_view operator*()
{
return view_.substr(tokenStart_, tokenEnd_ - tokenStart_);
}
Iterator &operator++()
{
if (tokenEnd_ == std::string::npos)
{
done_ = true;
return *this;
}
tokenStart_ = tokenEnd_ + delimiter_.size();
tokenEnd_ = view_.find(delimiter_, tokenStart_);
return *this;
}
bool operator!=(Iterator &other)
{
// We only check if both points to the end.
if (done_ && other.done_)
{
return false;
}
return true;
}
};
Iterator beginIter_;
StringSplit(std::string str, std::string delim)
: beginIter_{std::move(str), std::move(delim)}
{
}
Iterator begin()
{
return beginIter_;
}
Iterator end()
{
return Iterator{};
}
};
And example usage would be:
int main()
{
for (auto token : StringSplit{"<>foo<>bar<><>bar<><>baz<><>", "<>"})
{
std::cout << "TOKEN: '" << token << "'" << std::endl;
}
}
Which prints:
TOKEN: ''
TOKEN: 'foo'
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'baz'
TOKEN: ''
TOKEN: ''
It properly handles empty entries at the beginning and end of the string.
Here is an example of splitting a string with another string using Boost String Algorithms library and Boost Range library. The solution is inspired with (modest) suggestion from the the StringAlgo library documentation, see the Split section.
Below is a complete program with the split_with_string function as well as comprehensive test - try it with godbolt:
#include <iostream>
#include <string>
#include <vector>
#include <boost/algorithm/string.hpp>
#include <boost/range/iterator_range.hpp>
std::vector<std::string> split_with_string(std::string_view s, std::string_view search)
{
if (search.empty()) return {std::string{s}};
std::vector<boost::iterator_range<std::string_view::iterator>> found;
boost::algorithm::ifind_all(found, s, search);
if (found.empty()) return {};
std::vector<std::string> parts;
parts.reserve(found.size() + 2); // a bit more
std::string_view::iterator part_begin = s.cbegin(), part_end;
for (auto& split_found : found)
{
// do not skip empty extracts
part_end = split_found.begin();
parts.emplace_back(part_begin, part_end);
part_begin = split_found.end();
}
if (part_end != s.end())
parts.emplace_back(part_begin, s.end());
return parts;
}
#define TEST(expr) std::cout << ((!(expr)) ? "FAIL" : "PASS") << ": " #expr "\t" << std::endl
int main()
{
auto s0 = split_with_string("adsf-+qwret-+nvfkbdsj", "");
TEST(s0.size() == 1);
TEST(s0.front() == "adsf-+qwret-+nvfkbdsj");
auto s1 = split_with_string("adsf-+qwret-+nvfkbdsj", "-+");
TEST(s1.size() == 3);
TEST(s1.front() == "adsf");
TEST(s1.back() == "nvfkbdsj");
auto s2 = split_with_string("-+adsf-+qwret-+nvfkbdsj-+", "-+");
TEST(s2.size() == 5);
TEST(s2.front() == "");
TEST(s2.back() == "");
auto s3 = split_with_string("-+adsf-+qwret-+nvfkbdsj", "-+");
TEST(s3.size() == 4);
TEST(s3.front() == "");
TEST(s3.back() == "nvfkbdsj");
auto s4 = split_with_string("adsf-+qwret-+nvfkbdsj-+", "-+");
TEST(s4.size() == 4);
TEST(s4.front() == "adsf");
TEST(s4.back() == "");
auto s5 = split_with_string("dbo.abc", "dbo.");
TEST(s5.size() == 2);
TEST(s5.front() == "");
TEST(s5.back() == "abc");
auto s6 = split_with_string("dbo.abc", ".");
TEST(s6.size() == 2);
TEST(s6.front() == "dbo");
TEST(s6.back() == "abc");
}
Tests output:
PASS: s0.size() == 1
PASS: s0.front() == "adsf-+qwret-+nvfkbdsj"
PASS: s1.size() == 3
PASS: s1.front() == "adsf"
PASS: s1.back() == "nvfkbdsj"
PASS: s2.size() == 5
PASS: s2.front() == ""
PASS: s2.back() == ""
PASS: s3.size() == 4
PASS: s3.front() == ""
PASS: s3.back() == "nvfkbdsj"
PASS: s4.size() == 4
PASS: s4.front() == "adsf"
PASS: s4.back() == ""
PASS: s5.size() == 2
PASS: s5.front() == ""
PASS: s5.back() == "abc"
PASS: s6.size() == 2
PASS: s6.front() == "dbo"
PASS: s6.back() == "abc"
I am parsing a string in C++ using the following:
using namespace std;
string parsed,input="text to be parsed";
stringstream input_stringstream(input);
if (getline(input_stringstream,parsed,' '))
{
// do some processing.
}
Parsing with a single char delimiter is fine. But what if I want to use a string as delimiter.
Example: I want to split:
scott>=tiger
with >= as delimiter so that I can get scott and tiger.
You can use the std::string::find() function to find the position of your string delimiter, then use std::string::substr() to get a token.
Example:
std::string s = "scott>=tiger";
std::string delimiter = ">=";
std::string token = s.substr(0, s.find(delimiter)); // token is "scott"
The find(const string& str, size_t pos = 0) function returns the position of the first occurrence of str in the string, or npos if the string is not found.
The substr(size_t pos = 0, size_t n = npos) function returns a substring of the object, starting at position pos and of length npos.
If you have multiple delimiters, after you have extracted one token, you can remove it (delimiter included) to proceed with subsequent extractions (if you want to preserve the original string, just use s = s.substr(pos + delimiter.length());):
s.erase(0, s.find(delimiter) + delimiter.length());
This way you can easily loop to get each token.
Complete Example
std::string s = "scott>=tiger>=mushroom";
std::string delimiter = ">=";
size_t pos = 0;
std::string token;
while ((pos = s.find(delimiter)) != std::string::npos) {
token = s.substr(0, pos);
std::cout << token << std::endl;
s.erase(0, pos + delimiter.length());
}
std::cout << s << std::endl;
Output:
scott
tiger
mushroom
For string delimiter
Split string based on a string delimiter. Such as splitting string "adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih" based on string delimiter "-+", output will be {"adsf", "qwret", "nvfkbdsj", "orthdfjgh", "dfjrleih"}
#include <iostream>
#include <sstream>
#include <vector>
// for string delimiter
std::vector<std::string> split(std::string s, std::string delimiter) {
size_t pos_start = 0, pos_end, delim_len = delimiter.length();
std::string token;
std::vector<std::string> res;
while ((pos_end = s.find(delimiter, pos_start)) != std::string::npos) {
token = s.substr (pos_start, pos_end - pos_start);
pos_start = pos_end + delim_len;
res.push_back (token);
}
res.push_back (s.substr (pos_start));
return res;
}
int main() {
std::string str = "adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih";
std::string delimiter = "-+";
std::vector<std::string> v = split (str, delimiter);
for (auto i : v) cout << i << endl;
return 0;
}
**Output**
adsf
qwret
nvfkbdsj
orthdfjgh
dfjrleih
For single character delimiter
Split string based on a character delimiter. For example, splitting string "adsf+qwer+poui+fdgh" with delimiter "+" will output {"adsf", "qwer", "poui", "fdgh"}
#include <iostream>
#include <sstream>
#include <vector>
std::vector<std::string> split (const std::string &s, char delim) {
std::vector<std::string> result;
std::stringstream ss (s);
std::string item;
while (getline (ss, item, delim)) {
result.push_back (item);
}
return result;
}
int main() {
std::string str = "adsf+qwer+poui+fdgh";
std::vector<std::string> v = split (str, '+');
for (auto i : v) cout << i << endl;
return 0;
}
**Output**
adsf
qwer
poui
fdgh
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);
}
You can use next function to split string:
vector<string> split(const string& str, const string& delim)
{
vector<string> tokens;
size_t prev = 0, pos = 0;
do
{
pos = str.find(delim, prev);
if (pos == string::npos) pos = str.length();
string token = str.substr(prev, pos-prev);
if (!token.empty()) tokens.push_back(token);
prev = pos + delim.length();
}
while (pos < str.length() && prev < str.length());
return tokens;
}
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) {
std::regex regexz(regex_str);
return {std::sregex_token_iterator(str.begin(), str.end(), regexz, -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!
you can simply use substrings, characters, etc like normal, or use actual regular expressions to do the splitting.
its also concise and C++11!
A way of doing it with C++20:
#include <iostream>
#include <ranges>
#include <string_view>
int main()
{
std::string hello = "text to be parsed";
auto split = hello
| std::ranges::views::split(' ')
| std::ranges::views::transform([](auto&& str) { return std::string_view(&*str.begin(), std::ranges::distance(str)); });
for (auto&& word : split)
{
std::cout << word << std::endl;
}
}
See:
https://stackoverflow.com/a/48403210/10771848
https://en.cppreference.com/w/cpp/ranges/split_view
This code splits lines from text, and add everyone into a vector.
vector<string> split(char *phrase, string delimiter){
vector<string> list;
string s = string(phrase);
size_t pos = 0;
string token;
while ((pos = s.find(delimiter)) != string::npos) {
token = s.substr(0, pos);
list.push_back(token);
s.erase(0, pos + delimiter.length());
}
list.push_back(s);
return list;
}
Called by:
vector<string> listFilesMax = split(buffer, "\n");
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 startIndex = 0;
for (size_t found = i_str.find(i_delim); found != string::npos; found = i_str.find(i_delim, startIndex))
{
result.emplace_back(i_str.begin()+startIndex, i_str.begin()+found);
startIndex = found + i_delim.size();
}
if (startIndex != i_str.size())
result.emplace_back(i_str.begin()+startIndex, i_str.end());
return result;
}
strtok allows you to pass in multiple chars as delimiters. I bet if you passed in ">=" your example string would be split correctly (even though the > and = are counted as individual delimiters).
EDIT if you don't want to use c_str() to convert from string to char*, you can use substr and find_first_of to tokenize.
string token, mystring("scott>=tiger");
while(token != mystring){
token = mystring.substr(0,mystring.find_first_of(">="));
mystring = mystring.substr(mystring.find_first_of(">=") + 1);
printf("%s ",token.c_str());
}
I would use boost::tokenizer. Here's documentation explaining how to make an appropriate tokenizer function: http://www.boost.org/doc/libs/1_52_0/libs/tokenizer/tokenizerfunction.htm
Here's one that works for your case.
struct my_tokenizer_func
{
template<typename It>
bool operator()(It& next, It end, std::string & tok)
{
if (next == end)
return false;
char const * del = ">=";
auto pos = std::search(next, end, del, del + 2);
tok.assign(next, pos);
next = pos;
if (next != end)
std::advance(next, 2);
return true;
}
void reset() {}
};
int main()
{
std::string to_be_parsed = "1) one>=2) two>=3) three>=4) four";
for (auto i : boost::tokenizer<my_tokenizer_func>(to_be_parsed))
std::cout << i << '\n';
}
This should work perfectly for string (or single character) delimiters. Don't forget to include #include <sstream>.
std::string input = "Alfa=,+Bravo=,+Charlie=,+Delta";
std::string delimiter = "=,+";
std::istringstream ss(input);
std::string token;
std::string::iterator it;
while(std::getline(ss, token, *(it = delimiter.begin()))) {
std::cout << token << std::endl; // Token is extracted using '='
it++;
// Skip the rest of delimiter if exists ",+"
while(it != delimiter.end() and ss.peek() == *(it)) {
it++; ss.get();
}
}
The first while loop extracts a token using the first character of the string delimiter. The second while loop skips the rest of the delimiter and stops at the beginning of the next token.
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 != std::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]()
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);
Just in case in the future, someone wants out of the box function of Vincenzo Pii 's answer
#include <vector>
#include <string>
std::vector<std::string> SplitString(
std::string str,
std::string delimeter)
{
std::vector<std::string> splittedStrings = {};
size_t pos = 0;
while ((pos = str.find(delimeter)) != std::string::npos)
{
std::string token = str.substr(0, pos);
if (token.length() > 0)
splittedStrings.push_back(token);
str.erase(0, pos + delimeter.length());
}
if (str.length() > 0)
splittedStrings.push_back(str);
return splittedStrings;
}
I also fixed some bugs so that the function won't return an empty string if there is a delimiter at the start or the end of the string
This is a complete method that splits the string on any delimiter and returns a vector of the chopped up strings.
It is an adaptation from the answer from ryanbwork. However, his check for: if(token != mystring) gives wrong results if you have repeating elements in your string. This is my solution to that problem.
vector<string> Split(string mystring, string delimiter)
{
vector<string> subStringList;
string token;
while (true)
{
size_t findfirst = mystring.find_first_of(delimiter);
if (findfirst == string::npos) //find_first_of returns npos if it couldn't find the delimiter anymore
{
subStringList.push_back(mystring); //push back the final piece of mystring
return subStringList;
}
token = mystring.substr(0, mystring.find_first_of(delimiter));
mystring = mystring.substr(mystring.find_first_of(delimiter) + 1);
subStringList.push_back(token);
}
return subStringList;
}
Since this is the top-rated Stack Overflow Google search result for C++ split string or similar, I'll post a complete, copy/paste runnable example that shows both methods.
splitString uses stringstream (probably the better and easier option in most cases)
splitString2 uses find and substr (a more manual approach)
// SplitString.cpp
#include <iostream>
#include <vector>
#include <string>
#include <sstream>
// function prototypes
std::vector<std::string> splitString(const std::string& str, char delim);
std::vector<std::string> splitString2(const std::string& str, char delim);
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx);
int main(void)
{
// Test cases - all will pass
std::string str = "ab,cd,ef";
//std::string str = "abcdef";
//std::string str = "";
//std::string str = ",cd,ef";
//std::string str = "ab,cd,"; // behavior of splitString and splitString2 is different for this final case only, if this case matters to you choose which one you need as applicable
std::vector<std::string> tokens = splitString(str, ',');
std::cout << "tokens: " << "\n";
if (tokens.empty())
{
std::cout << "(tokens is empty)" << "\n";
}
else
{
for (auto& token : tokens)
{
if (token == "") std::cout << "(empty string)" << "\n";
else std::cout << token << "\n";
}
}
return 0;
}
std::vector<std::string> splitString(const std::string& str, char delim)
{
std::vector<std::string> tokens;
if (str == "") return tokens;
std::string currentToken;
std::stringstream ss(str);
while (std::getline(ss, currentToken, delim))
{
tokens.push_back(currentToken);
}
return tokens;
}
std::vector<std::string> splitString2(const std::string& str, char delim)
{
std::vector<std::string> tokens;
if (str == "") return tokens;
int leftIdx = 0;
int delimIdx = str.find(delim);
int rightIdx;
while (delimIdx != std::string::npos)
{
rightIdx = delimIdx - 1;
std::string token = getSubstring(str, leftIdx, rightIdx);
tokens.push_back(token);
// prep for next time around
leftIdx = delimIdx + 1;
delimIdx = str.find(delim, delimIdx + 1);
}
rightIdx = str.size() - 1;
std::string token = getSubstring(str, leftIdx, rightIdx);
tokens.push_back(token);
return tokens;
}
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx)
{
return str.substr(leftIdx, rightIdx - leftIdx + 1);
}
Yet another answer: Here I'm using find_first_not_of string function which returns the position of the first character that does not match any of the characters specified in the delim.
size_t find_first_not_of(const string& delim, size_t pos = 0) const noexcept;
Example:
int main()
{
size_t start = 0, end = 0;
std::string str = "scott>=tiger>=cat";
std::string delim = ">=";
while ((start = str.find_first_not_of(delim, end)) != std::string::npos)
{
end = str.find(delim, start); // finds the 'first' occurance from the 'start'
std::cout << str.substr(start, end - start)<<std::endl; // extract substring
}
return 0;
}
Output:
scott
tiger
cat
I make this solution. It is very simple, all the prints/values are in the loop (no need to check after the loop).
#include <iostream>
#include <string>
using std::cout;
using std::string;
int main() {
string s = "it-+is-+working!";
string d = "-+";
int firstFindI = 0;
int secendFindI = 0;
while (secendFindI != string::npos)
{
secendFindI = s.find(d, firstFindI);
cout << s.substr(firstFindI, secendFindI - firstFindI) << "\n"; // print sliced part
firstFindI = secendFindI + d.size(); // add to the search index
}
}
Thanks to #SteveWard for improving this answer.
This is similar to other answers but it's using string_view. So these are just views for the original string. Similar to the c++20 example. Though this would be a c++17 example. (edit to skip empty matches)
#include <algorithm>
#include <iostream>
#include <string_view>
#include <vector>
std::vector<std::string_view> split(std::string_view buffer,
const std::string_view delimeter = " ") {
std::vector<std::string_view> ret{};
std::decay_t<decltype(std::string_view::npos)> pos{};
while ((pos = buffer.find(delimeter)) != std::string_view::npos) {
const auto match = buffer.substr(0, pos);
if (!match.empty()) ret.push_back(match);
buffer = buffer.substr(pos + delimeter.size());
}
if (!buffer.empty()) ret.push_back(buffer);
return ret;
}
int main() {
const auto split_values = split("1 2 3 4 5 6 7 8 9 10 ");
std::for_each(split_values.begin(), split_values.end(),
[](const auto& str) { std::cout << str << '\n'; });
return split_values.size();
}
If you do not want to modify the string (as in the answer by Vincenzo Pii) and want to output the last token as well, you may want to use this approach:
inline std::vector<std::string> splitString( const std::string &s, const std::string &delimiter ){
std::vector<std::string> ret;
size_t start = 0;
size_t end = 0;
size_t len = 0;
std::string token;
do{ end = s.find(delimiter,start);
len = end - start;
token = s.substr(start, len);
ret.emplace_back( token );
start += len + delimiter.length();
std::cout << token << std::endl;
}while ( end != std::string::npos );
return ret;
}
Here's a concise split function. I decided to have back to back delimiters return as an empty string but you could easily check that if the substring is empty and not add it to the vector if it is.
#include <vector>
#include <string>
using namespace std;
vector<string> split(string to_split, string delimiter) {
size_t pos = 0;
vector<string> matches{};
do {
pos = to_split.find(delimiter);
int change_end;
if (pos == string::npos) {
pos = to_split.length() - 1;
change_end = 1;
}
else {
change_end = 0;
}
matches.push_back(to_split.substr(0, pos+change_end));
to_split.erase(0, pos+1);
}
while (!to_split.empty());
return matches;
}
This method use string find and string substr
vector<string> split(const string& str,const string delim){
vector<string> vtokens;
size_t start = 0;
size_t end = 0;
while((end = str.find(delim,start))!=string::npos){
vtokens.push_back(str.substr(start,end-start));
start = end +1;
}
vtokens.push_back(str.substr(start));
return vtokens;
}
#include<iostream>
#include<algorithm>
using namespace std;
int split_count(string str,char delimit){
return count(str.begin(),str.end(),delimit);
}
void split(string str,char delimit,string res[]){
int a=0,i=0;
while(a<str.size()){
res[i]=str.substr(a,str.find(delimit));
a+=res[i].size()+1;
i++;
}
}
int main(){
string a="abc.xyz.mno.def";
int x=split_count(a,'.')+1;
string res[x];
split(a,'.',res);
for(int i=0;i<x;i++)
cout<<res[i]<<endl;
return 0;
}
P.S: Works only if the lengths of the strings after splitting are equal
std::vector<std::string> parse(std::string str,std::string delim){
std::vector<std::string> tokens;
char *str_c = strdup(str.c_str());
char* token = NULL;
token = strtok(str_c, delim.c_str());
while (token != NULL) {
tokens.push_back(std::string(token));
token = strtok(NULL, delim.c_str());
}
delete[] str_c;
return tokens;
}
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;
}
i use pointer arithmetic. inner while for string delimeter if you satify with char delim just remove inner while simply. i hope it is correct. if you notice any mistake or improve please leave the comment.
std::vector<std::string> split(std::string s, std::string delim)
{
char *p = &s[0];
char *d = &delim[0];
std::vector<std::string> res = {""};
do
{
bool is_delim = true;
char *pp = p;
char *dd = d;
while (*dd && is_delim == true)
if (*pp++ != *dd++)
is_delim = false;
if (is_delim)
{
p = pp - 1;
res.push_back("");
}
else
*(res.rbegin()) += *p;
} while (*p++);
return res;
}
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.push_back(std::forward<T>(t)), void()) {
c.push_back(std::forward<T>(t));
}
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.insert(std::forward<T>(t)), void()) {
c.insert(std::forward<T>(t));
}
template<typename Container>
Container splitR(const std::string& input, const std::string& delims) {
Container out;
size_t delims_len = delims.size();
auto begIdx = 0u;
auto endIdx = input.find(delims, begIdx);
if (endIdx == std::string::npos && input.size() != 0u) {
insert_in_container(out, input);
}
else {
size_t w = 0;
while (endIdx != std::string::npos) {
w = endIdx - begIdx;
if (w != 0) insert_in_container(out, input.substr(begIdx, w));
begIdx = endIdx + delims_len;
endIdx = input.find(delims, begIdx);
}
w = input.length() - begIdx;
if (w != 0) insert_in_container(out, input.substr(begIdx, w));
}
return out;
}
A simpler solution would be -
You can use strtok to delimit on the basis of multichar delimiter.
Remember to use strdup so that the orignal string isn't mutated.
#include <stdio.h>
#include <string.h>
const char* str = "scott>=tiger";
char *token = strtok(strdup(str), ">=");
while (token != NULL)
{
printf("%s\n", token);
token = strtok(NULL, ">=");
}
I looked through the answers and haven't seen an iterator based approach that can be fed into a range loop, so I made one.
This uses C++17 string_views so it shouldn't allocate copies of the string.
struct StringSplit
{
struct Iterator
{
size_t tokenStart_ = 0;
size_t tokenEnd_ = 0;
std::string str_;
std::string_view view_;
std::string delimiter_;
bool done_ = false;
Iterator()
{
// End iterator.
done_ = true;
}
Iterator(std::string str, std::string delimiter)
: str_{std::move(str)}, view_{str_}, delimiter_{
std::move(delimiter)}
{
tokenEnd_ = view_.find(delimiter_, tokenStart_);
}
std::string_view operator*()
{
return view_.substr(tokenStart_, tokenEnd_ - tokenStart_);
}
Iterator &operator++()
{
if (tokenEnd_ == std::string::npos)
{
done_ = true;
return *this;
}
tokenStart_ = tokenEnd_ + delimiter_.size();
tokenEnd_ = view_.find(delimiter_, tokenStart_);
return *this;
}
bool operator!=(Iterator &other)
{
// We only check if both points to the end.
if (done_ && other.done_)
{
return false;
}
return true;
}
};
Iterator beginIter_;
StringSplit(std::string str, std::string delim)
: beginIter_{std::move(str), std::move(delim)}
{
}
Iterator begin()
{
return beginIter_;
}
Iterator end()
{
return Iterator{};
}
};
And example usage would be:
int main()
{
for (auto token : StringSplit{"<>foo<>bar<><>bar<><>baz<><>", "<>"})
{
std::cout << "TOKEN: '" << token << "'" << std::endl;
}
}
Which prints:
TOKEN: ''
TOKEN: 'foo'
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'baz'
TOKEN: ''
TOKEN: ''
It properly handles empty entries at the beginning and end of the string.
Here is an example of splitting a string with another string using Boost String Algorithms library and Boost Range library. The solution is inspired with (modest) suggestion from the the StringAlgo library documentation, see the Split section.
Below is a complete program with the split_with_string function as well as comprehensive test - try it with godbolt:
#include <iostream>
#include <string>
#include <vector>
#include <boost/algorithm/string.hpp>
#include <boost/range/iterator_range.hpp>
std::vector<std::string> split_with_string(std::string_view s, std::string_view search)
{
if (search.empty()) return {std::string{s}};
std::vector<boost::iterator_range<std::string_view::iterator>> found;
boost::algorithm::ifind_all(found, s, search);
if (found.empty()) return {};
std::vector<std::string> parts;
parts.reserve(found.size() + 2); // a bit more
std::string_view::iterator part_begin = s.cbegin(), part_end;
for (auto& split_found : found)
{
// do not skip empty extracts
part_end = split_found.begin();
parts.emplace_back(part_begin, part_end);
part_begin = split_found.end();
}
if (part_end != s.end())
parts.emplace_back(part_begin, s.end());
return parts;
}
#define TEST(expr) std::cout << ((!(expr)) ? "FAIL" : "PASS") << ": " #expr "\t" << std::endl
int main()
{
auto s0 = split_with_string("adsf-+qwret-+nvfkbdsj", "");
TEST(s0.size() == 1);
TEST(s0.front() == "adsf-+qwret-+nvfkbdsj");
auto s1 = split_with_string("adsf-+qwret-+nvfkbdsj", "-+");
TEST(s1.size() == 3);
TEST(s1.front() == "adsf");
TEST(s1.back() == "nvfkbdsj");
auto s2 = split_with_string("-+adsf-+qwret-+nvfkbdsj-+", "-+");
TEST(s2.size() == 5);
TEST(s2.front() == "");
TEST(s2.back() == "");
auto s3 = split_with_string("-+adsf-+qwret-+nvfkbdsj", "-+");
TEST(s3.size() == 4);
TEST(s3.front() == "");
TEST(s3.back() == "nvfkbdsj");
auto s4 = split_with_string("adsf-+qwret-+nvfkbdsj-+", "-+");
TEST(s4.size() == 4);
TEST(s4.front() == "adsf");
TEST(s4.back() == "");
auto s5 = split_with_string("dbo.abc", "dbo.");
TEST(s5.size() == 2);
TEST(s5.front() == "");
TEST(s5.back() == "abc");
auto s6 = split_with_string("dbo.abc", ".");
TEST(s6.size() == 2);
TEST(s6.front() == "dbo");
TEST(s6.back() == "abc");
}
Tests output:
PASS: s0.size() == 1
PASS: s0.front() == "adsf-+qwret-+nvfkbdsj"
PASS: s1.size() == 3
PASS: s1.front() == "adsf"
PASS: s1.back() == "nvfkbdsj"
PASS: s2.size() == 5
PASS: s2.front() == ""
PASS: s2.back() == ""
PASS: s3.size() == 4
PASS: s3.front() == ""
PASS: s3.back() == "nvfkbdsj"
PASS: s4.size() == 4
PASS: s4.front() == "adsf"
PASS: s4.back() == ""
PASS: s5.size() == 2
PASS: s5.front() == ""
PASS: s5.back() == "abc"
PASS: s6.size() == 2
PASS: s6.front() == "dbo"
PASS: s6.back() == "abc"
So basically I want to create a format function that accepts a string, and replaces words in that string with whatever the user wants to be replaced. At first I had some issues with non-deferencable iterators until I realized that when you change the the size of a string you can invalid any iterators. It doesn't throw anymore exceptions now now the output is the same as the input. Any advice???
string& formatFn(string& s, string& oldWord, string& newWord)
{
string word = "";
for (auto iter1 = s.begin(); iter1 != s.end(); ++iter1)
{
string tmpWord = "";
if (!isblank(*iter1)) // Testing for whitespace
{
tmpWord += *iter1;
if (tmpWord == oldWord)
{
string::iterator beg = iter1 - word.size();
string::iterator end = iter1;
auto sIter = s.erase(beg, end); // Get the position returned by erase
auto i = sIter - s.begin(); // Get an index
s = s.insert(s[i], newWord);
}
}
if (isblank(*iter1))
{
tmpWord.clear();
}
}
return s;
}
If you already use string why don`t use all methods?
for (auto it = text.find(o_text); it != string::npos; it = text.find(o_text)){
text.replace(it, o_text.size(), n_text);
}
string::iterator beg = iter1 - word.size();
I'm not sure what word actually does. You are trying to delete oldWord, right? Then it should be:
string::iterator beg = iter1 - oldWord.size();
EDIT : This is an improved version of your code:
string formatFn(const string& s, const string& oldWord, const string& newWord) {
string result = ""; // holds the string we want to return
string word = ""; // while iterating over 's', holds the current word
for (auto iter1 = s.begin(); iter1 != s.end(); ++iter1) {
if (!isblank(*iter1))
word += *iter1;
else { // if it is a whitespace, it must be the end of some word
// if 'word' is not same as 'oldword', just append it
// otherwise append 'newWord' instead
if (word == oldWord)
result += newWord;
else
result += word;
result += *iter1;
word.clear(); // reset 'word' to hold the next word in s
}
}
// the end of the string might not end with a whitespace, so the last word
// might be skipped if you don't make this test
if (word == oldWord)
result += newWord;
else
result += word;
return result;
}
You are over-complicating it:
std::string replace_all(std::string s, const std::string& sOld, const std::string& sNew)
{
std::size_t p = s.find(sOld);
while (p != std::string::npos)
{
s.replace(p, sOld.length(), sNew);
p = s.find(sOld, p + sNew.length());
}
return s;
}
If you are looking to replace whole words only (which your current attempt will not do):
#include <iostream>
#include <string>
bool test(const std::string& s, const std::string& sOld, std::size_t pos)
{
return (pos == 0 || !::isalpha(s[pos - 1])) && (!::isalpha(s[pos + sOld.length()]) || pos + sOld.length() >= s.length());
}
std::size_t find_word(const std::string& s, const std::string& sOld, std::size_t pos)
{
pos = s.find(sOld, pos);
while (pos != std::string::npos && (!test(s, sOld, pos) && pos < s.length()))
{
pos++;
pos = s.find(sOld, pos);
}
return pos;
}
std::string replace_all(std::string s, const std::string& sOld, const std::string& sNew)
{
std::size_t p = find_word(s, sOld, 0);
while (p != std::string::npos && p < s.length())
{
s.replace(p, sOld.length(), sNew);
p = find_word(s, sOld, p + sNew.length());
}
return s;
}
int main()
{
std::string sOrig = "eat Heat eat beat sweat cheat eat";
std::string sOld = "eat";
std::string sNew = "ate";
std::string sResult = replace_all(sOrig, sOld, sNew);
std::cout << "Result: " << sResult << std::endl;
// Output: "ate Heat ate beat sweat cheat ate"
return 0;
}
I am parsing a string in C++ using the following:
using namespace std;
string parsed,input="text to be parsed";
stringstream input_stringstream(input);
if (getline(input_stringstream,parsed,' '))
{
// do some processing.
}
Parsing with a single char delimiter is fine. But what if I want to use a string as delimiter.
Example: I want to split:
scott>=tiger
with >= as delimiter so that I can get scott and tiger.
You can use the std::string::find() function to find the position of your string delimiter, then use std::string::substr() to get a token.
Example:
std::string s = "scott>=tiger";
std::string delimiter = ">=";
std::string token = s.substr(0, s.find(delimiter)); // token is "scott"
The find(const string& str, size_t pos = 0) function returns the position of the first occurrence of str in the string, or npos if the string is not found.
The substr(size_t pos = 0, size_t n = npos) function returns a substring of the object, starting at position pos and of length npos.
If you have multiple delimiters, after you have extracted one token, you can remove it (delimiter included) to proceed with subsequent extractions (if you want to preserve the original string, just use s = s.substr(pos + delimiter.length());):
s.erase(0, s.find(delimiter) + delimiter.length());
This way you can easily loop to get each token.
Complete Example
std::string s = "scott>=tiger>=mushroom";
std::string delimiter = ">=";
size_t pos = 0;
std::string token;
while ((pos = s.find(delimiter)) != std::string::npos) {
token = s.substr(0, pos);
std::cout << token << std::endl;
s.erase(0, pos + delimiter.length());
}
std::cout << s << std::endl;
Output:
scott
tiger
mushroom
For string delimiter
Split string based on a string delimiter. Such as splitting string "adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih" based on string delimiter "-+", output will be {"adsf", "qwret", "nvfkbdsj", "orthdfjgh", "dfjrleih"}
#include <iostream>
#include <sstream>
#include <vector>
// for string delimiter
std::vector<std::string> split(std::string s, std::string delimiter) {
size_t pos_start = 0, pos_end, delim_len = delimiter.length();
std::string token;
std::vector<std::string> res;
while ((pos_end = s.find(delimiter, pos_start)) != std::string::npos) {
token = s.substr (pos_start, pos_end - pos_start);
pos_start = pos_end + delim_len;
res.push_back (token);
}
res.push_back (s.substr (pos_start));
return res;
}
int main() {
std::string str = "adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih";
std::string delimiter = "-+";
std::vector<std::string> v = split (str, delimiter);
for (auto i : v) cout << i << endl;
return 0;
}
**Output**
adsf
qwret
nvfkbdsj
orthdfjgh
dfjrleih
For single character delimiter
Split string based on a character delimiter. For example, splitting string "adsf+qwer+poui+fdgh" with delimiter "+" will output {"adsf", "qwer", "poui", "fdgh"}
#include <iostream>
#include <sstream>
#include <vector>
std::vector<std::string> split (const std::string &s, char delim) {
std::vector<std::string> result;
std::stringstream ss (s);
std::string item;
while (getline (ss, item, delim)) {
result.push_back (item);
}
return result;
}
int main() {
std::string str = "adsf+qwer+poui+fdgh";
std::vector<std::string> v = split (str, '+');
for (auto i : v) cout << i << endl;
return 0;
}
**Output**
adsf
qwer
poui
fdgh
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);
}
You can use next function to split string:
vector<string> split(const string& str, const string& delim)
{
vector<string> tokens;
size_t prev = 0, pos = 0;
do
{
pos = str.find(delim, prev);
if (pos == string::npos) pos = str.length();
string token = str.substr(prev, pos-prev);
if (!token.empty()) tokens.push_back(token);
prev = pos + delim.length();
}
while (pos < str.length() && prev < str.length());
return tokens;
}
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) {
std::regex regexz(regex_str);
return {std::sregex_token_iterator(str.begin(), str.end(), regexz, -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!
you can simply use substrings, characters, etc like normal, or use actual regular expressions to do the splitting.
its also concise and C++11!
A way of doing it with C++20:
#include <iostream>
#include <ranges>
#include <string_view>
int main()
{
std::string hello = "text to be parsed";
auto split = hello
| std::ranges::views::split(' ')
| std::ranges::views::transform([](auto&& str) { return std::string_view(&*str.begin(), std::ranges::distance(str)); });
for (auto&& word : split)
{
std::cout << word << std::endl;
}
}
See:
https://stackoverflow.com/a/48403210/10771848
https://en.cppreference.com/w/cpp/ranges/split_view
This code splits lines from text, and add everyone into a vector.
vector<string> split(char *phrase, string delimiter){
vector<string> list;
string s = string(phrase);
size_t pos = 0;
string token;
while ((pos = s.find(delimiter)) != string::npos) {
token = s.substr(0, pos);
list.push_back(token);
s.erase(0, pos + delimiter.length());
}
list.push_back(s);
return list;
}
Called by:
vector<string> listFilesMax = split(buffer, "\n");
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 startIndex = 0;
for (size_t found = i_str.find(i_delim); found != string::npos; found = i_str.find(i_delim, startIndex))
{
result.emplace_back(i_str.begin()+startIndex, i_str.begin()+found);
startIndex = found + i_delim.size();
}
if (startIndex != i_str.size())
result.emplace_back(i_str.begin()+startIndex, i_str.end());
return result;
}
strtok allows you to pass in multiple chars as delimiters. I bet if you passed in ">=" your example string would be split correctly (even though the > and = are counted as individual delimiters).
EDIT if you don't want to use c_str() to convert from string to char*, you can use substr and find_first_of to tokenize.
string token, mystring("scott>=tiger");
while(token != mystring){
token = mystring.substr(0,mystring.find_first_of(">="));
mystring = mystring.substr(mystring.find_first_of(">=") + 1);
printf("%s ",token.c_str());
}
I would use boost::tokenizer. Here's documentation explaining how to make an appropriate tokenizer function: http://www.boost.org/doc/libs/1_52_0/libs/tokenizer/tokenizerfunction.htm
Here's one that works for your case.
struct my_tokenizer_func
{
template<typename It>
bool operator()(It& next, It end, std::string & tok)
{
if (next == end)
return false;
char const * del = ">=";
auto pos = std::search(next, end, del, del + 2);
tok.assign(next, pos);
next = pos;
if (next != end)
std::advance(next, 2);
return true;
}
void reset() {}
};
int main()
{
std::string to_be_parsed = "1) one>=2) two>=3) three>=4) four";
for (auto i : boost::tokenizer<my_tokenizer_func>(to_be_parsed))
std::cout << i << '\n';
}
This should work perfectly for string (or single character) delimiters. Don't forget to include #include <sstream>.
std::string input = "Alfa=,+Bravo=,+Charlie=,+Delta";
std::string delimiter = "=,+";
std::istringstream ss(input);
std::string token;
std::string::iterator it;
while(std::getline(ss, token, *(it = delimiter.begin()))) {
std::cout << token << std::endl; // Token is extracted using '='
it++;
// Skip the rest of delimiter if exists ",+"
while(it != delimiter.end() and ss.peek() == *(it)) {
it++; ss.get();
}
}
The first while loop extracts a token using the first character of the string delimiter. The second while loop skips the rest of the delimiter and stops at the beginning of the next token.
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 != std::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]()
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);
Just in case in the future, someone wants out of the box function of Vincenzo Pii 's answer
#include <vector>
#include <string>
std::vector<std::string> SplitString(
std::string str,
std::string delimeter)
{
std::vector<std::string> splittedStrings = {};
size_t pos = 0;
while ((pos = str.find(delimeter)) != std::string::npos)
{
std::string token = str.substr(0, pos);
if (token.length() > 0)
splittedStrings.push_back(token);
str.erase(0, pos + delimeter.length());
}
if (str.length() > 0)
splittedStrings.push_back(str);
return splittedStrings;
}
I also fixed some bugs so that the function won't return an empty string if there is a delimiter at the start or the end of the string
This is a complete method that splits the string on any delimiter and returns a vector of the chopped up strings.
It is an adaptation from the answer from ryanbwork. However, his check for: if(token != mystring) gives wrong results if you have repeating elements in your string. This is my solution to that problem.
vector<string> Split(string mystring, string delimiter)
{
vector<string> subStringList;
string token;
while (true)
{
size_t findfirst = mystring.find_first_of(delimiter);
if (findfirst == string::npos) //find_first_of returns npos if it couldn't find the delimiter anymore
{
subStringList.push_back(mystring); //push back the final piece of mystring
return subStringList;
}
token = mystring.substr(0, mystring.find_first_of(delimiter));
mystring = mystring.substr(mystring.find_first_of(delimiter) + 1);
subStringList.push_back(token);
}
return subStringList;
}
Since this is the top-rated Stack Overflow Google search result for C++ split string or similar, I'll post a complete, copy/paste runnable example that shows both methods.
splitString uses stringstream (probably the better and easier option in most cases)
splitString2 uses find and substr (a more manual approach)
// SplitString.cpp
#include <iostream>
#include <vector>
#include <string>
#include <sstream>
// function prototypes
std::vector<std::string> splitString(const std::string& str, char delim);
std::vector<std::string> splitString2(const std::string& str, char delim);
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx);
int main(void)
{
// Test cases - all will pass
std::string str = "ab,cd,ef";
//std::string str = "abcdef";
//std::string str = "";
//std::string str = ",cd,ef";
//std::string str = "ab,cd,"; // behavior of splitString and splitString2 is different for this final case only, if this case matters to you choose which one you need as applicable
std::vector<std::string> tokens = splitString(str, ',');
std::cout << "tokens: " << "\n";
if (tokens.empty())
{
std::cout << "(tokens is empty)" << "\n";
}
else
{
for (auto& token : tokens)
{
if (token == "") std::cout << "(empty string)" << "\n";
else std::cout << token << "\n";
}
}
return 0;
}
std::vector<std::string> splitString(const std::string& str, char delim)
{
std::vector<std::string> tokens;
if (str == "") return tokens;
std::string currentToken;
std::stringstream ss(str);
while (std::getline(ss, currentToken, delim))
{
tokens.push_back(currentToken);
}
return tokens;
}
std::vector<std::string> splitString2(const std::string& str, char delim)
{
std::vector<std::string> tokens;
if (str == "") return tokens;
int leftIdx = 0;
int delimIdx = str.find(delim);
int rightIdx;
while (delimIdx != std::string::npos)
{
rightIdx = delimIdx - 1;
std::string token = getSubstring(str, leftIdx, rightIdx);
tokens.push_back(token);
// prep for next time around
leftIdx = delimIdx + 1;
delimIdx = str.find(delim, delimIdx + 1);
}
rightIdx = str.size() - 1;
std::string token = getSubstring(str, leftIdx, rightIdx);
tokens.push_back(token);
return tokens;
}
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx)
{
return str.substr(leftIdx, rightIdx - leftIdx + 1);
}
Yet another answer: Here I'm using find_first_not_of string function which returns the position of the first character that does not match any of the characters specified in the delim.
size_t find_first_not_of(const string& delim, size_t pos = 0) const noexcept;
Example:
int main()
{
size_t start = 0, end = 0;
std::string str = "scott>=tiger>=cat";
std::string delim = ">=";
while ((start = str.find_first_not_of(delim, end)) != std::string::npos)
{
end = str.find(delim, start); // finds the 'first' occurance from the 'start'
std::cout << str.substr(start, end - start)<<std::endl; // extract substring
}
return 0;
}
Output:
scott
tiger
cat
I make this solution. It is very simple, all the prints/values are in the loop (no need to check after the loop).
#include <iostream>
#include <string>
using std::cout;
using std::string;
int main() {
string s = "it-+is-+working!";
string d = "-+";
int firstFindI = 0;
int secendFindI = 0;
while (secendFindI != string::npos)
{
secendFindI = s.find(d, firstFindI);
cout << s.substr(firstFindI, secendFindI - firstFindI) << "\n"; // print sliced part
firstFindI = secendFindI + d.size(); // add to the search index
}
}
Thanks to #SteveWard for improving this answer.
This is similar to other answers but it's using string_view. So these are just views for the original string. Similar to the c++20 example. Though this would be a c++17 example. (edit to skip empty matches)
#include <algorithm>
#include <iostream>
#include <string_view>
#include <vector>
std::vector<std::string_view> split(std::string_view buffer,
const std::string_view delimeter = " ") {
std::vector<std::string_view> ret{};
std::decay_t<decltype(std::string_view::npos)> pos{};
while ((pos = buffer.find(delimeter)) != std::string_view::npos) {
const auto match = buffer.substr(0, pos);
if (!match.empty()) ret.push_back(match);
buffer = buffer.substr(pos + delimeter.size());
}
if (!buffer.empty()) ret.push_back(buffer);
return ret;
}
int main() {
const auto split_values = split("1 2 3 4 5 6 7 8 9 10 ");
std::for_each(split_values.begin(), split_values.end(),
[](const auto& str) { std::cout << str << '\n'; });
return split_values.size();
}
If you do not want to modify the string (as in the answer by Vincenzo Pii) and want to output the last token as well, you may want to use this approach:
inline std::vector<std::string> splitString( const std::string &s, const std::string &delimiter ){
std::vector<std::string> ret;
size_t start = 0;
size_t end = 0;
size_t len = 0;
std::string token;
do{ end = s.find(delimiter,start);
len = end - start;
token = s.substr(start, len);
ret.emplace_back( token );
start += len + delimiter.length();
std::cout << token << std::endl;
}while ( end != std::string::npos );
return ret;
}
Here's a concise split function. I decided to have back to back delimiters return as an empty string but you could easily check that if the substring is empty and not add it to the vector if it is.
#include <vector>
#include <string>
using namespace std;
vector<string> split(string to_split, string delimiter) {
size_t pos = 0;
vector<string> matches{};
do {
pos = to_split.find(delimiter);
int change_end;
if (pos == string::npos) {
pos = to_split.length() - 1;
change_end = 1;
}
else {
change_end = 0;
}
matches.push_back(to_split.substr(0, pos+change_end));
to_split.erase(0, pos+1);
}
while (!to_split.empty());
return matches;
}
This method use string find and string substr
vector<string> split(const string& str,const string delim){
vector<string> vtokens;
size_t start = 0;
size_t end = 0;
while((end = str.find(delim,start))!=string::npos){
vtokens.push_back(str.substr(start,end-start));
start = end +1;
}
vtokens.push_back(str.substr(start));
return vtokens;
}
#include<iostream>
#include<algorithm>
using namespace std;
int split_count(string str,char delimit){
return count(str.begin(),str.end(),delimit);
}
void split(string str,char delimit,string res[]){
int a=0,i=0;
while(a<str.size()){
res[i]=str.substr(a,str.find(delimit));
a+=res[i].size()+1;
i++;
}
}
int main(){
string a="abc.xyz.mno.def";
int x=split_count(a,'.')+1;
string res[x];
split(a,'.',res);
for(int i=0;i<x;i++)
cout<<res[i]<<endl;
return 0;
}
P.S: Works only if the lengths of the strings after splitting are equal
std::vector<std::string> parse(std::string str,std::string delim){
std::vector<std::string> tokens;
char *str_c = strdup(str.c_str());
char* token = NULL;
token = strtok(str_c, delim.c_str());
while (token != NULL) {
tokens.push_back(std::string(token));
token = strtok(NULL, delim.c_str());
}
delete[] str_c;
return tokens;
}
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;
}
i use pointer arithmetic. inner while for string delimeter if you satify with char delim just remove inner while simply. i hope it is correct. if you notice any mistake or improve please leave the comment.
std::vector<std::string> split(std::string s, std::string delim)
{
char *p = &s[0];
char *d = &delim[0];
std::vector<std::string> res = {""};
do
{
bool is_delim = true;
char *pp = p;
char *dd = d;
while (*dd && is_delim == true)
if (*pp++ != *dd++)
is_delim = false;
if (is_delim)
{
p = pp - 1;
res.push_back("");
}
else
*(res.rbegin()) += *p;
} while (*p++);
return res;
}
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.push_back(std::forward<T>(t)), void()) {
c.push_back(std::forward<T>(t));
}
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.insert(std::forward<T>(t)), void()) {
c.insert(std::forward<T>(t));
}
template<typename Container>
Container splitR(const std::string& input, const std::string& delims) {
Container out;
size_t delims_len = delims.size();
auto begIdx = 0u;
auto endIdx = input.find(delims, begIdx);
if (endIdx == std::string::npos && input.size() != 0u) {
insert_in_container(out, input);
}
else {
size_t w = 0;
while (endIdx != std::string::npos) {
w = endIdx - begIdx;
if (w != 0) insert_in_container(out, input.substr(begIdx, w));
begIdx = endIdx + delims_len;
endIdx = input.find(delims, begIdx);
}
w = input.length() - begIdx;
if (w != 0) insert_in_container(out, input.substr(begIdx, w));
}
return out;
}
A simpler solution would be -
You can use strtok to delimit on the basis of multichar delimiter.
Remember to use strdup so that the orignal string isn't mutated.
#include <stdio.h>
#include <string.h>
const char* str = "scott>=tiger";
char *token = strtok(strdup(str), ">=");
while (token != NULL)
{
printf("%s\n", token);
token = strtok(NULL, ">=");
}
I looked through the answers and haven't seen an iterator based approach that can be fed into a range loop, so I made one.
This uses C++17 string_views so it shouldn't allocate copies of the string.
struct StringSplit
{
struct Iterator
{
size_t tokenStart_ = 0;
size_t tokenEnd_ = 0;
std::string str_;
std::string_view view_;
std::string delimiter_;
bool done_ = false;
Iterator()
{
// End iterator.
done_ = true;
}
Iterator(std::string str, std::string delimiter)
: str_{std::move(str)}, view_{str_}, delimiter_{
std::move(delimiter)}
{
tokenEnd_ = view_.find(delimiter_, tokenStart_);
}
std::string_view operator*()
{
return view_.substr(tokenStart_, tokenEnd_ - tokenStart_);
}
Iterator &operator++()
{
if (tokenEnd_ == std::string::npos)
{
done_ = true;
return *this;
}
tokenStart_ = tokenEnd_ + delimiter_.size();
tokenEnd_ = view_.find(delimiter_, tokenStart_);
return *this;
}
bool operator!=(Iterator &other)
{
// We only check if both points to the end.
if (done_ && other.done_)
{
return false;
}
return true;
}
};
Iterator beginIter_;
StringSplit(std::string str, std::string delim)
: beginIter_{std::move(str), std::move(delim)}
{
}
Iterator begin()
{
return beginIter_;
}
Iterator end()
{
return Iterator{};
}
};
And example usage would be:
int main()
{
for (auto token : StringSplit{"<>foo<>bar<><>bar<><>baz<><>", "<>"})
{
std::cout << "TOKEN: '" << token << "'" << std::endl;
}
}
Which prints:
TOKEN: ''
TOKEN: 'foo'
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'baz'
TOKEN: ''
TOKEN: ''
It properly handles empty entries at the beginning and end of the string.
Here is an example of splitting a string with another string using Boost String Algorithms library and Boost Range library. The solution is inspired with (modest) suggestion from the the StringAlgo library documentation, see the Split section.
Below is a complete program with the split_with_string function as well as comprehensive test - try it with godbolt:
#include <iostream>
#include <string>
#include <vector>
#include <boost/algorithm/string.hpp>
#include <boost/range/iterator_range.hpp>
std::vector<std::string> split_with_string(std::string_view s, std::string_view search)
{
if (search.empty()) return {std::string{s}};
std::vector<boost::iterator_range<std::string_view::iterator>> found;
boost::algorithm::ifind_all(found, s, search);
if (found.empty()) return {};
std::vector<std::string> parts;
parts.reserve(found.size() + 2); // a bit more
std::string_view::iterator part_begin = s.cbegin(), part_end;
for (auto& split_found : found)
{
// do not skip empty extracts
part_end = split_found.begin();
parts.emplace_back(part_begin, part_end);
part_begin = split_found.end();
}
if (part_end != s.end())
parts.emplace_back(part_begin, s.end());
return parts;
}
#define TEST(expr) std::cout << ((!(expr)) ? "FAIL" : "PASS") << ": " #expr "\t" << std::endl
int main()
{
auto s0 = split_with_string("adsf-+qwret-+nvfkbdsj", "");
TEST(s0.size() == 1);
TEST(s0.front() == "adsf-+qwret-+nvfkbdsj");
auto s1 = split_with_string("adsf-+qwret-+nvfkbdsj", "-+");
TEST(s1.size() == 3);
TEST(s1.front() == "adsf");
TEST(s1.back() == "nvfkbdsj");
auto s2 = split_with_string("-+adsf-+qwret-+nvfkbdsj-+", "-+");
TEST(s2.size() == 5);
TEST(s2.front() == "");
TEST(s2.back() == "");
auto s3 = split_with_string("-+adsf-+qwret-+nvfkbdsj", "-+");
TEST(s3.size() == 4);
TEST(s3.front() == "");
TEST(s3.back() == "nvfkbdsj");
auto s4 = split_with_string("adsf-+qwret-+nvfkbdsj-+", "-+");
TEST(s4.size() == 4);
TEST(s4.front() == "adsf");
TEST(s4.back() == "");
auto s5 = split_with_string("dbo.abc", "dbo.");
TEST(s5.size() == 2);
TEST(s5.front() == "");
TEST(s5.back() == "abc");
auto s6 = split_with_string("dbo.abc", ".");
TEST(s6.size() == 2);
TEST(s6.front() == "dbo");
TEST(s6.back() == "abc");
}
Tests output:
PASS: s0.size() == 1
PASS: s0.front() == "adsf-+qwret-+nvfkbdsj"
PASS: s1.size() == 3
PASS: s1.front() == "adsf"
PASS: s1.back() == "nvfkbdsj"
PASS: s2.size() == 5
PASS: s2.front() == ""
PASS: s2.back() == ""
PASS: s3.size() == 4
PASS: s3.front() == ""
PASS: s3.back() == "nvfkbdsj"
PASS: s4.size() == 4
PASS: s4.front() == "adsf"
PASS: s4.back() == ""
PASS: s5.size() == 2
PASS: s5.front() == ""
PASS: s5.back() == "abc"
PASS: s6.size() == 2
PASS: s6.front() == "dbo"
PASS: s6.back() == "abc"
What is the right way to split a string into a vector of strings? Delimiter is space or comma.
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;
}
split("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;
}
Here is my variant that work somelike as explode function in PHP, we provide given string and delimiters list.
std::vector< std::string > explode(const std::string& data, const std::string& delimiters) {
auto is_delim = [&](auto & c) { return delimiters.find(c) != std::string::npos; };
std::vector< std::string > result;
for (std::string::size_type i(0), len(data.length()), pos(0); i <= len; i++) {
if (is_delim(data[i]) || i == len) {
auto tok = data.substr(pos, i - pos);
if ( !tok.empty() )
result.push_back( tok );
pos = i + 1;
}
} return result;
}
example of usage
std::string test_delimiters("hello, there is lots of, delimiters, that may be even together, ");
auto dem_res = explode(test_delimiters, " ,"); // space or comma
for (auto word : dem_res) {
std::cout << word << '\n';
} std::cout << "end\n";
the ouput:
hello
there
is
lots
of
delimiters
that
may
be
even
together
end