I'm trying to iterate over the words of a string.
The string can be assumed to be composed of words separated by whitespace.
Note that I'm not interested in C string functions or that kind of character manipulation/access. Also, please give precedence to elegance over efficiency in your answer.
The best solution I have right now is:
#include <iostream>
#include <sstream>
#include <string>
using namespace std;
int main()
{
string s = "Somewhere down the road";
istringstream iss(s);
do
{
string subs;
iss >> subs;
cout << "Substring: " << subs << endl;
} while (iss);
}
Is there a more elegant way to do this?
Everyone answered for predefined string input. I think this answer will help someone for scanned input.
I used tokens vector for holding string tokens. It's optional.
#include <bits/stdc++.h>
using namespace std ;
int main()
{
string str, token ;
getline(cin, str) ; // get the string as input
istringstream ss(str); // insert the string into tokenizer
vector<string> tokens; // vector tokens holds the tokens
while (ss >> token) tokens.push_back(token); // splits the tokens
for(auto x : tokens) cout << x << endl ; // prints the tokens
return 0;
}
sample input:
port city international university
sample output:
port
city
international
university
Note that by default this will work for only space as the delimiter. you can use custom delimiter. For that, you have customized the code. let the delimiter be ','. so use
char delimiter = ',' ;
while(getline(ss, token, delimiter)) tokens.push_back(token) ;
instead of
while (ss >> token) tokens.push_back(token);
If you like to use boost, but want to use a whole string as delimiter (instead of single characters as in most of the previously proposed solutions), you can use the boost_split_iterator.
Example code including convenient template:
#include <iostream>
#include <vector>
#include <boost/algorithm/string.hpp>
template<typename _OutputIterator>
inline void split(
const std::string& str,
const std::string& delim,
_OutputIterator result)
{
using namespace boost::algorithm;
typedef split_iterator<std::string::const_iterator> It;
for(It iter=make_split_iterator(str, first_finder(delim, is_equal()));
iter!=It();
++iter)
{
*(result++) = boost::copy_range<std::string>(*iter);
}
}
int main(int argc, char* argv[])
{
using namespace std;
vector<string> splitted;
split("HelloFOOworldFOO!", "FOO", back_inserter(splitted));
// or directly to console, for example
split("HelloFOOworldFOO!", "FOO", ostream_iterator<string>(cout, "\n"));
return 0;
}
Using std::string_view and Eric Niebler's range-v3 library:
https://wandbox.org/permlink/kW5lwRCL1pxjp2pW
#include <iostream>
#include <string>
#include <string_view>
#include "range/v3/view.hpp"
#include "range/v3/algorithm.hpp"
int main() {
std::string s = "Somewhere down the range v3 library";
ranges::for_each(s
| ranges::view::split(' ')
| ranges::view::transform([](auto &&sub) {
return std::string_view(&*sub.begin(), ranges::distance(sub));
}),
[](auto s) {std::cout << "Substring: " << s << "\n";}
);
}
By using a range for loop instead of ranges::for_each algorithm:
#include <iostream>
#include <string>
#include <string_view>
#include "range/v3/view.hpp"
int main()
{
std::string str = "Somewhere down the range v3 library";
for (auto s : str | ranges::view::split(' ')
| ranges::view::transform([](auto&& sub) { return std::string_view(&*sub.begin(), ranges::distance(sub)); }
))
{
std::cout << "Substring: " << s << "\n";
}
}
I use the following
void split(string in, vector<string>& parts, char separator) {
string::iterator ts, curr;
ts = curr = in.begin();
for(; curr <= in.end(); curr++ ) {
if( (curr == in.end() || *curr == separator) && curr > ts )
parts.push_back( string( ts, curr ));
if( curr == in.end() )
break;
if( *curr == separator ) ts = curr + 1;
}
}
PlasmaHH, I forgot to include the extra check( curr > ts) for removing tokens with whitespace.
This is my favorite way to iterate through a string. You can do whatever you want per word.
string line = "a line of text to iterate through";
string word;
istringstream iss(line, istringstream::in);
while( iss >> word )
{
// Do something on `word` here...
}
No Boost, no string streams, just the standard C library cooperating together with std::string and std::list: C library functions for easy analysis, C++ data types for easy memory management.
Whitespace is considered to be any combination of newlines, tabs and spaces. The set of whitespace characters is established by the wschars variable.
#include <string>
#include <list>
#include <iostream>
#include <cstring>
using namespace std;
const char *wschars = "\t\n ";
list<string> split(const string &str)
{
const char *cstr = str.c_str();
list<string> out;
while (*cstr) { // while remaining string not empty
size_t toklen;
cstr += strspn(cstr, wschars); // skip leading whitespace
toklen = strcspn(cstr, wschars); // figure out token length
if (toklen) // if we have a token, add to list
out.push_back(string(cstr, toklen));
cstr += toklen; // skip over token
}
// ran out of string; return list
return out;
}
int main(int argc, char **argv)
{
list<string> li = split(argv[1]);
for (list<string>::iterator i = li.begin(); i != li.end(); i++)
cout << "{" << *i << "}" << endl;
return 0;
}
Run:
$ ./split ""
$ ./split "a"
{a}
$ ./split " a "
{a}
$ ./split " a b"
{a}
{b}
$ ./split " a b c"
{a}
{b}
{c}
$ ./split " a b c d "
{a}
{b}
{c}
{d}
Tail-recursive version of split (itself split into two functions). All destructive manipulation of variables is gone, except for the pushing of strings into the list!
void split_rec(const char *cstr, list<string> &li)
{
if (*cstr) {
const size_t leadsp = strspn(cstr, wschars);
const size_t toklen = strcspn(cstr + leadsp, wschars);
if (toklen)
li.push_back(string(cstr + leadsp, toklen));
split_rec(cstr + leadsp + toklen, li);
}
}
list<string> split(const string &str)
{
list<string> out;
split_rec(str.c_str(), out);
return out;
}
#include <vector>
#include <string>
#include <sstream>
int main()
{
std::string str("Split me by whitespaces");
std::string buf; // Have a buffer string
std::stringstream ss(str); // Insert the string into a stream
std::vector<std::string> tokens; // Create vector to hold our words
while (ss >> buf)
tokens.push_back(buf);
return 0;
}
This is my versión taken the source of Kev:
#include <string>
#include <vector>
void split(vector<string> &result, string str, char delim ) {
string tmp;
string::iterator i;
result.clear();
for(i = str.begin(); i <= str.end(); ++i) {
if((const char)*i != delim && i != str.end()) {
tmp += *i;
} else {
result.push_back(tmp);
tmp = "";
}
}
}
After, call the function and do something with it:
vector<string> hosts;
split(hosts, "192.168.1.2,192.168.1.3", ',');
for( size_t i = 0; i < hosts.size(); i++){
cout << "Connecting host : " << hosts.at(i) << "..." << endl;
}
This is an extension of one of the top answers. It now supports setting a max number of returned elements, N. The last bit of the string will end up in the Nth element. The MAXELEMENTS parameter is optional, if set at default 0 it will return an unlimited amount of elements. :-)
.h:
class Myneatclass {
public:
static std::vector<std::string>& split(const std::string &s, char delim, std::vector<std::string> &elems, const size_t MAXELEMENTS = 0);
static std::vector<std::string> split(const std::string &s, char delim, const size_t MAXELEMENTS = 0);
};
.cpp:
std::vector<std::string>& Myneatclass::split(const std::string &s, char delim, std::vector<std::string> &elems, const size_t MAXELEMENTS) {
std::stringstream ss(s);
std::string item;
while (std::getline(ss, item, delim)) {
elems.push_back(item);
if (MAXELEMENTS > 0 && !ss.eof() && elems.size() + 1 >= MAXELEMENTS) {
std::getline(ss, item);
elems.push_back(item);
break;
}
}
return elems;
}
std::vector<std::string> Myneatclass::split(const std::string &s, char delim, const size_t MAXELEMENTS) {
std::vector<std::string> elems;
split(s, delim, elems, MAXELEMENTS);
return elems;
}
My code is:
#include <list>
#include <string>
template<class StringType = std::string, class ContainerType = std::list<StringType> >
class DSplitString:public ContainerType
{
public:
explicit DSplitString(const StringType& strString, char cChar, bool bSkipEmptyParts = true)
{
size_t iPos = 0;
size_t iPos_char = 0;
while(StringType::npos != (iPos_char = strString.find(cChar, iPos)))
{
StringType strTemp = strString.substr(iPos, iPos_char - iPos);
if((bSkipEmptyParts && !strTemp.empty()) || (!bSkipEmptyParts))
push_back(strTemp);
iPos = iPos_char + 1;
}
}
explicit DSplitString(const StringType& strString, const StringType& strSub, bool bSkipEmptyParts = true)
{
size_t iPos = 0;
size_t iPos_char = 0;
while(StringType::npos != (iPos_char = strString.find(strSub, iPos)))
{
StringType strTemp = strString.substr(iPos, iPos_char - iPos);
if((bSkipEmptyParts && !strTemp.empty()) || (!bSkipEmptyParts))
push_back(strTemp);
iPos = iPos_char + strSub.length();
}
}
};
Example:
#include <iostream>
#include <string>
int _tmain(int argc, _TCHAR* argv[])
{
DSplitString<> aa("doicanhden1;doicanhden2;doicanhden3;", ';');
for each (std::string var in aa)
{
std::cout << var << std::endl;
}
std::cin.get();
return 0;
}
I like the following because it puts the results into a vector, supports a string as a delim and gives control over keeping empty values. But, it doesn't look as good then.
#include <ostream>
#include <string>
#include <vector>
#include <algorithm>
#include <iterator>
using namespace std;
vector<string> split(const string& s, const string& delim, const bool keep_empty = true) {
vector<string> result;
if (delim.empty()) {
result.push_back(s);
return result;
}
string::const_iterator substart = s.begin(), subend;
while (true) {
subend = search(substart, s.end(), delim.begin(), delim.end());
string temp(substart, subend);
if (keep_empty || !temp.empty()) {
result.push_back(temp);
}
if (subend == s.end()) {
break;
}
substart = subend + delim.size();
}
return result;
}
int main() {
const vector<string> words = split("So close no matter how far", " ");
copy(words.begin(), words.end(), ostream_iterator<string>(cout, "\n"));
}
Of course, Boost has a split() that works partially like that. And, if by 'white-space', you really do mean any type of white-space, using Boost's split with is_any_of() works great.
void splitString(string str, char delim, string array[], const int arraySize)
{
int delimPosition, subStrSize, subStrStart = 0;
for (int index = 0; delimPosition != -1; index++)
{
delimPosition = str.find(delim, subStrStart);
subStrSize = delimPosition - subStrStart;
array[index] = str.substr(subStrStart, subStrSize);
subStrStart =+ (delimPosition + 1);
}
}
The STL does not have such a method available already.
However, you can either use C's strtok() function by using the std::string::c_str() member, or you can write your own. Here is a code sample I found after a quick Google search ("STL string split"):
void Tokenize(const string& str,
vector<string>& tokens,
const string& delimiters = " ")
{
// Skip delimiters at beginning.
string::size_type lastPos = str.find_first_not_of(delimiters, 0);
// Find first "non-delimiter".
string::size_type pos = str.find_first_of(delimiters, lastPos);
while (string::npos != pos || string::npos != lastPos)
{
// Found a token, add it to the vector.
tokens.push_back(str.substr(lastPos, pos - lastPos));
// Skip delimiters. Note the "not_of"
lastPos = str.find_first_not_of(delimiters, pos);
// Find next "non-delimiter"
pos = str.find_first_of(delimiters, lastPos);
}
}
Taken from: http://oopweb.com/CPP/Documents/CPPHOWTO/Volume/C++Programming-HOWTO-7.html
If you have questions about the code sample, leave a comment and I will explain.
And just because it does not implement a typedef called iterator or overload the << operator does not mean it is bad code. I use C functions quite frequently. For example, printf and scanf both are faster than std::cin and std::cout (significantly), the fopen syntax is a lot more friendly for binary types, and they also tend to produce smaller EXEs.
Don't get sold on this "Elegance over performance" deal.
Here is a split function that:
ignores empty tokens (can easily be changed)
template<typename T>
vector<T>
split(const T & str, const T & delimiters) {
vector<T> v;
typename T::size_type start = 0;
auto pos = str.find_first_of(delimiters, start);
while(pos != T::npos) {
if(pos != start) // ignore empty tokens
v.emplace_back(str, start, pos - start);
start = pos + 1;
pos = str.find_first_of(delimiters, start);
}
if(start < str.length()) // ignore trailing delimiter
v.emplace_back(str, start, str.length() - start); // add what's left of the string
return v;
}
Example usage:
vector<string> v = split<string>("Hello, there; World", ";,");
vector<wstring> v = split<wstring>(L"Hello, there; World", L";,");
Everyone answered for predefined string input. I think this answer will help someone for scanned input.
I used tokens vector for holding string tokens. It's optional.
#include <bits/stdc++.h>
using namespace std ;
int main()
{
string str, token ;
getline(cin, str) ; // get the string as input
istringstream ss(str); // insert the string into tokenizer
vector<string> tokens; // vector tokens holds the tokens
while (ss >> token) tokens.push_back(token); // splits the tokens
for(auto x : tokens) cout << x << endl ; // prints the tokens
return 0;
}
sample input:
port city international university
sample output:
port
city
international
university
Note that by default this will work for only space as the delimiter. you can use custom delimiter. For that, you have customized the code. let the delimiter be ','. so use
char delimiter = ',' ;
while(getline(ss, token, delimiter)) tokens.push_back(token) ;
instead of
while (ss >> token) tokens.push_back(token);
This answer takes the string and puts it into a vector of strings. It uses the boost library.
#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));
The code below uses strtok() to split a string into tokens and stores the tokens in a vector.
#include <iostream>
#include <algorithm>
#include <vector>
#include <string>
using namespace std;
char one_line_string[] = "hello hi how are you nice weather we are having ok then bye";
char seps[] = " ,\t\n";
char *token;
int main()
{
vector<string> vec_String_Lines;
token = strtok( one_line_string, seps );
cout << "Extracting and storing data in a vector..\n\n\n";
while( token != NULL )
{
vec_String_Lines.push_back(token);
token = strtok( NULL, seps );
}
cout << "Displaying end result in vector line storage..\n\n";
for ( int i = 0; i < vec_String_Lines.size(); ++i)
cout << vec_String_Lines[i] << "\n";
cout << "\n\n\n";
return 0;
}
Using std::string_view and Eric Niebler's range-v3 library:
https://wandbox.org/permlink/kW5lwRCL1pxjp2pW
#include <iostream>
#include <string>
#include <string_view>
#include "range/v3/view.hpp"
#include "range/v3/algorithm.hpp"
int main() {
std::string s = "Somewhere down the range v3 library";
ranges::for_each(s
| ranges::view::split(' ')
| ranges::view::transform([](auto &&sub) {
return std::string_view(&*sub.begin(), ranges::distance(sub));
}),
[](auto s) {std::cout << "Substring: " << s << "\n";}
);
}
By using a range for loop instead of ranges::for_each algorithm:
#include <iostream>
#include <string>
#include <string_view>
#include "range/v3/view.hpp"
int main()
{
std::string str = "Somewhere down the range v3 library";
for (auto s : str | ranges::view::split(' ')
| ranges::view::transform([](auto&& sub) { return std::string_view(&*sub.begin(), ranges::distance(sub)); }
))
{
std::cout << "Substring: " << s << "\n";
}
}
Here's my approach, cut and split:
string cut (string& str, const string& del)
{
string f = str;
if (in.find_first_of(del) != string::npos)
{
f = str.substr(0,str.find_first_of(del));
str = str.substr(str.find_first_of(del)+del.length());
}
return f;
}
vector<string> split (const string& in, const string& del=" ")
{
vector<string> out();
string t = in;
while (t.length() > del.length())
out.push_back(cut(t,del));
return out;
}
BTW, if there's something I can do to optimize this ..
We can use strtok in c++ ,
#include <iostream>
#include <cstring>
using namespace std;
int main()
{
char str[]="Mickey M;12034;911416313;M;01a;9001;NULL;0;13;12;0;CPP,C;MSC,3D;FEND,BEND,SEC;";
char *pch = strtok (str,";,");
while (pch != NULL)
{
cout<<pch<<"\n";
pch = strtok (NULL, ";,");
}
return 0;
}
The following is a much better way to do this. It can take any character, and doesn't split lines unless you want. No special libraries needed (well, besides std, but who really considers that an extra library), no pointers, no references, and it's static. Just simple plain C++.
#pragma once
#include <vector>
#include <sstream>
using namespace std;
class Helpers
{
public:
static vector<string> split(string s, char delim)
{
stringstream temp (stringstream::in | stringstream::out);
vector<string> elems(0);
if (s.size() == 0 || delim == 0)
return elems;
for(char c : s)
{
if(c == delim)
{
elems.push_back(temp.str());
temp = stringstream(stringstream::in | stringstream::out);
}
else
temp << c;
}
if (temp.str().size() > 0)
elems.push_back(temp.str());
return elems;
}
//Splits string s with a list of delimiters in delims (it's just a list, like if we wanted to
//split at the following letters, a, b, c we would make delims="abc".
static vector<string> split(string s, string delims)
{
stringstream temp (stringstream::in | stringstream::out);
vector<string> elems(0);
bool found;
if(s.size() == 0 || delims.size() == 0)
return elems;
for(char c : s)
{
found = false;
for(char d : delims)
{
if (c == d)
{
elems.push_back(temp.str());
temp = stringstream(stringstream::in | stringstream::out);
found = true;
break;
}
}
if(!found)
temp << c;
}
if(temp.str().size() > 0)
elems.push_back(temp.str());
return elems;
}
};
For a ridiculously large and probably redundant version, try a lot of for loops.
string stringlist[10];
int count = 0;
for (int i = 0; i < sequence.length(); i++)
{
if (sequence[i] == ' ')
{
stringlist[count] = sequence.substr(0, i);
sequence.erase(0, i+1);
i = 0;
count++;
}
else if (i == sequence.length()-1) // Last word
{
stringlist[count] = sequence.substr(0, i+1);
}
}
It isn't pretty, but by and large (Barring punctuation and a slew of other bugs) it works!
This is my favorite way to iterate through a string. You can do whatever you want per word.
string line = "a line of text to iterate through";
string word;
istringstream iss(line, istringstream::in);
while( iss >> word )
{
// Do something on `word` here...
}
The code below uses strtok() to split a string into tokens and stores the tokens in a vector.
#include <iostream>
#include <algorithm>
#include <vector>
#include <string>
using namespace std;
char one_line_string[] = "hello hi how are you nice weather we are having ok then bye";
char seps[] = " ,\t\n";
char *token;
int main()
{
vector<string> vec_String_Lines;
token = strtok( one_line_string, seps );
cout << "Extracting and storing data in a vector..\n\n\n";
while( token != NULL )
{
vec_String_Lines.push_back(token);
token = strtok( NULL, seps );
}
cout << "Displaying end result in vector line storage..\n\n";
for ( int i = 0; i < vec_String_Lines.size(); ++i)
cout << vec_String_Lines[i] << "\n";
cout << "\n\n\n";
return 0;
}
Based on Galik's answer I made this. This is mostly here so I don't have to keep writing it again and again. It's crazy that C++ still doesn't have a native split function. Features:
"\r\n")#include <string>
#include <vector>
#include <algorithm>
std::vector<std::string> split(const std::string& s, const std::string& delims)
{
using namespace std;
vector<string> v;
// Start of an element.
size_t elemStart = 0;
// We start searching from the end of the previous element, which
// initially is the start of the string.
size_t elemEnd = 0;
// Find the first non-delim, i.e. the start of an element, after the end of the previous element.
while((elemStart = s.find_first_not_of(delims, elemEnd)) != string::npos)
{
// Find the first delem, i.e. the end of the element (or if this fails it is the end of the string).
elemEnd = s.find_first_of(delims, elemStart);
// Add it.
v.emplace_back(s, elemStart, elemEnd == string::npos ? string::npos : elemEnd - elemStart);
}
// When there are no more non-spaces, we are done.
return v;
}
For those with whom it does not sit well to sacrifice all efficiency for code size and see "efficient" as a type of elegance, the following should hit a sweet spot (and I think the template container class is an awesomely elegant addition.):
template < class ContainerT >
void tokenize(const std::string& str, ContainerT& tokens,
const std::string& delimiters = " ", bool trimEmpty = false)
{
std::string::size_type pos, lastPos = 0, length = str.length();
using value_type = typename ContainerT::value_type;
using size_type = typename ContainerT::size_type;
while(lastPos < length + 1)
{
pos = str.find_first_of(delimiters, lastPos);
if(pos == std::string::npos)
{
pos = length;
}
if(pos != lastPos || !trimEmpty)
tokens.push_back(value_type(str.data()+lastPos,
(size_type)pos-lastPos ));
lastPos = pos + 1;
}
}
I usually choose to use std::vector<std::string> types as my second parameter (ContainerT)... but list<> is way faster than vector<> for when direct access is not needed, and you can even create your own string class and use something like std::list<subString> where subString does not do any copies for incredible speed increases.
It's more than double as fast as the fastest tokenize on this page and almost 5 times faster than some others. Also with the perfect parameter types you can eliminate all string and list copies for additional speed increases.
Additionally it does not do the (extremely inefficient) return of result, but rather it passes the tokens as a reference, thus also allowing you to build up tokens using multiple calls if you so wished.
Lastly it allows you to specify whether to trim empty tokens from the results via a last optional parameter.
All it needs is std::string... the rest are optional. It does not use streams or the boost library, but is flexible enough to be able to accept some of these foreign types naturally.
I have a 2 lines solution to this problem:
char sep = ' ';
std::string s="1 This is an example";
for(size_t p=0, q=0; p!=s.npos; p=q)
std::cout << s.substr(p+(p!=0), (q=s.find(sep, p+1))-p-(p!=0)) << std::endl;
Then instead of printing you can put it in a vector.
The stringstream can be convenient if you need to parse the string by non-space symbols:
string s = "Name:JAck; Spouse:Susan; ...";
string dummy, name, spouse;
istringstream iss(s);
getline(iss, dummy, ':');
getline(iss, name, ';');
getline(iss, dummy, ':');
getline(iss, spouse, ';')
Using std::stringstream as you have works perfectly fine, and do exactly what you wanted. If you're just looking for different way of doing things though, you can use std::find()/std::find_first_of() and std::string::substr().
Here's an example:
#include <iostream>
#include <string>
int main()
{
std::string s("Somewhere down the road");
std::string::size_type prev_pos = 0, pos = 0;
while( (pos = s.find(' ', pos)) != std::string::npos )
{
std::string substring( s.substr(prev_pos, pos-prev_pos) );
std::cout << substring << '\n';
prev_pos = ++pos;
}
std::string substring( s.substr(prev_pos, pos-prev_pos) ); // Last word
std::cout << substring << '\n';
return 0;
}
my general implementation for string and u32string ~, using the boost::algorithm::split signature.
template<typename CharT, typename UnaryPredicate>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
UnaryPredicate predicate)
{
using ST = std::basic_string<CharT>;
using std::swap;
std::vector<ST> tmp_result;
auto iter = s.cbegin(),
end_iter = s.cend();
while (true)
{
/**
* edge case: empty str -> push an empty str and exit.
*/
auto find_iter = find_if(iter, end_iter, predicate);
tmp_result.emplace_back(iter, find_iter);
if (find_iter == end_iter) { break; }
iter = ++find_iter;
}
swap(tmp_result, split_result);
}
template<typename CharT>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
const std::basic_string<CharT>& char_candidate)
{
std::unordered_set<CharT> candidate_set(char_candidate.cbegin(),
char_candidate.cend());
auto predicate = [&candidate_set](const CharT& c) {
return candidate_set.count(c) > 0U;
};
return split(split_result, s, predicate);
}
template<typename CharT>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
const CharT* literals)
{
return split(split_result, s, std::basic_string<CharT>(literals));
}
I've been searching for a way to split a string by a separator of any length, so I started writing it from scratch, as existing solutions didn't suit me.
Here is my little algorithm, using only STL:
//use like this
//std::vector<std::wstring> vec = Split<std::wstring> (L"Hello##world##!", L"##");
template <typename valueType>
static std::vector <valueType> Split (valueType text, const valueType& delimiter)
{
std::vector <valueType> tokens;
size_t pos = 0;
valueType token;
while ((pos = text.find(delimiter)) != valueType::npos)
{
token = text.substr(0, pos);
tokens.push_back (token);
text.erase(0, pos + delimiter.length());
}
tokens.push_back (text);
return tokens;
}
It can be used with separator of any length and form, as far as I've tested. Instantiate with either string or wstring type.
All the algorithm does is it searches for the delimiter, gets the part of the string that is up to the delimiter, deletes the delimiter and searches again until it finds it no more.
Of course, you can use any number of whitespaces for the delimiter.
I hope it helps.
Just for convenience:
template<class V, typename T>
bool in(const V &v, const T &el) {
return std::find(v.begin(), v.end(), el) != v.end();
}
The actual splitting based on multiple delimiters:
std::vector<std::string> split(const std::string &s,
const std::vector<char> &delims) {
std::vector<std::string> res;
auto stuff = [&delims](char c) { return !in(delims, c); };
auto space = [&delims](char c) { return in(delims, c); };
auto first = std::find_if(s.begin(), s.end(), stuff);
while (first != s.end()) {
auto last = std::find_if(first, s.end(), space);
res.push_back(std::string(first, last));
first = std::find_if(last + 1, s.end(), stuff);
}
return res;
}
The usage:
int main() {
std::string s = " aaa, bb cc ";
for (auto el: split(s, {' ', ','}))
std::cout << el << std::endl;
return 0;
}
very late to the party here I know but I was thinking about the most elegant way of doing this if you were given a range of delimiters rather than whitespace, and using nothing more than the standard library.
Here are my thoughts:
To split words into a string vector by a sequence of delimiters:
template<class Container>
std::vector<std::string> split_by_delimiters(const std::string& input, const Container& delimiters)
{
std::vector<std::string> result;
for (auto current = begin(input) ; current != end(input) ; )
{
auto first = find_if(current, end(input), not_in(delimiters));
if (first == end(input)) break;
auto last = find_if(first, end(input), is_in(delimiters));
result.emplace_back(first, last);
current = last;
}
return result;
}
to split the other way, by providing a sequence of valid characters:
template<class Container>
std::vector<std::string> split_by_valid_chars(const std::string& input, const Container& valid_chars)
{
std::vector<std::string> result;
for (auto current = begin(input) ; current != end(input) ; )
{
auto first = find_if(current, end(input), is_in(valid_chars));
if (first == end(input)) break;
auto last = find_if(first, end(input), not_in(valid_chars));
result.emplace_back(first, last);
current = last;
}
return result;
}
is_in and not_in are defined thus:
namespace detail {
template<class Container>
struct is_in {
is_in(const Container& charset)
: _charset(charset)
{}
bool operator()(char c) const
{
return find(begin(_charset), end(_charset), c) != end(_charset);
}
const Container& _charset;
};
template<class Container>
struct not_in {
not_in(const Container& charset)
: _charset(charset)
{}
bool operator()(char c) const
{
return find(begin(_charset), end(_charset), c) == end(_charset);
}
const Container& _charset;
};
}
template<class Container>
detail::not_in<Container> not_in(const Container& c)
{
return detail::not_in<Container>(c);
}
template<class Container>
detail::is_in<Container> is_in(const Container& c)
{
return detail::is_in<Container>(c);
}
I have just written a fine example of how to split a char by symbol, which then places each array of chars (words seperated by your symbol) into a vector. For simplicity i made the vector type of std string.
I hope this helps and is readable to you.
#include <vector>
#include <string>
#include <iostream>
void push(std::vector<std::string> &WORDS, std::string &TMP){
WORDS.push_back(TMP);
TMP = "";
}
std::vector<std::string> mySplit(char STRING[]){
std::vector<std::string> words;
std::string s;
for(unsigned short i = 0; i < strlen(STRING); i++){
if(STRING[i] != ' '){
s += STRING[i];
}else{
push(words, s);
}
}
push(words, s);//Used to get last split
return words;
}
int main(){
char string[] = "My awesome string.";
std::cout << mySplit(string)[2];
std::cin.get();
return 0;
}
This is a function I wrote that helps me do a lot. It helped me when doing protocol for WebSockets.
using namespace std;
#include <iostream>
#include <vector>
#include <sstream>
#include <string>
vector<string> split ( string input , string split_id ) {
vector<string> result;
int i = 0;
bool add;
string temp;
stringstream ss;
size_t found;
string real;
int r = 0;
while ( i != input.length() ) {
add = false;
ss << input.at(i);
temp = ss.str();
found = temp.find(split_id);
if ( found != string::npos ) {
add = true;
real.append ( temp , 0 , found );
} else if ( r > 0 && ( i+1 ) == input.length() ) {
add = true;
real.append ( temp , 0 , found );
}
if ( add ) {
result.push_back(real);
ss.str(string());
ss.clear();
temp.clear();
real.clear();
r = 0;
}
i++;
r++;
}
return result;
}
int main() {
string s = "S,o,m,e,w,h,e,r,e, down the road \n In a really big C++ house. \n Lives a little old lady. \n That no one ever knew. \n She comes outside. \n In the very hot sun. \n\n\n\n\n\n\n\n And throws C++ at us. \n The End. FIN.";
vector < string > Token;
Token = split ( s , "," );
for ( int i = 0 ; i < Token.size(); i++) cout << Token.at(i) << endl;
cout << endl << Token.size();
int a;
cin >> a;
return a;
}
When dealing with whitespace as separator, the obvious answer of using std::istream_iterator<T> is already given and voted up a lot. Of course, elements may not be separated by whitespace but by some separator instead. I didn't spot any answer which just redefines the meaning of whitespace to be said separator and then uses the conventional approach.
The way to change what streams consider whitespace, you'd simply change the stream's std::locale using (std::istream::imbue()) with a std::ctype<char> facet with its own definition of what whitespace means (it can be done for std::ctype<wchar_t>, too, but its is actually slightly different because std::ctype<char> is table-driven while std::ctype<wchar_t> is driven by virtual functions).
#include <iostream>
#include <algorithm>
#include <iterator>
#include <sstream>
#include <locale>
struct whitespace_mask {
std::ctype_base::mask mask_table[std::ctype<char>::table_size];
whitespace_mask(std::string const& spaces) {
std::ctype_base::mask* table = this->mask_table;
std::ctype_base::mask const* tab
= std::use_facet<std::ctype<char>>(std::locale()).table();
for (std::size_t i(0); i != std::ctype<char>::table_size; ++i) {
table[i] = tab[i] & ~std::ctype_base::space;
}
std::for_each(spaces.begin(), spaces.end(), [=](unsigned char c) {
table[c] |= std::ctype_base::space;
});
}
};
class whitespace_facet
: private whitespace_mask
, public std::ctype<char> {
public:
whitespace_facet(std::string const& spaces)
: whitespace_mask(spaces)
, std::ctype<char>(this->mask_table) {
}
};
struct whitespace {
std::string spaces;
whitespace(std::string const& spaces): spaces(spaces) {}
};
std::istream& operator>>(std::istream& in, whitespace const& ws) {
std::locale loc(in.getloc(), new whitespace_facet(ws.spaces));
in.imbue(loc);
return in;
}
// everything above would probably go into a utility library...
int main() {
std::istringstream in("a, b, c, d, e");
std::copy(std::istream_iterator<std::string>(in >> whitespace(", ")),
std::istream_iterator<std::string>(),
std::ostream_iterator<std::string>(std::cout, "\n"));
std::istringstream pipes("a b c| d |e e");
std::copy(std::istream_iterator<std::string>(pipes >> whitespace("|")),
std::istream_iterator<std::string>(),
std::ostream_iterator<std::string>(std::cout, "\n"));
}
Most of the code is for packaging up a general purpose tool providing soft delimiters: multiple delimiters in a row are merged. There is no way to produce an empty sequence. When different delimiters are needed within a stream, you'd probably use differently set up streams using a shared stream buffer:
void f(std::istream& in) {
std::istream pipes(in.rdbuf());
pipes >> whitespace("|");
std::istream comma(in.rdbuf());
comma >> whitespace(",");
std::string s0, s1;
if (pipes >> s0 >> std::ws // read up to first pipe and ignore sequence of pipes
&& comma >> s1 >> std::ws) { // read up to first comma and ignore commas
// ...
}
}
Using std::stringstream as you have works perfectly fine, and do exactly what you wanted. If you're just looking for different way of doing things though, you can use std::find()/std::find_first_of() and std::string::substr().
Here's an example:
#include <iostream>
#include <string>
int main()
{
std::string s("Somewhere down the road");
std::string::size_type prev_pos = 0, pos = 0;
while( (pos = s.find(' ', pos)) != std::string::npos )
{
std::string substring( s.substr(prev_pos, pos-prev_pos) );
std::cout << substring << '\n';
prev_pos = ++pos;
}
std::string substring( s.substr(prev_pos, pos-prev_pos) ); // Last word
std::cout << substring << '\n';
return 0;
}
My implementation can be an alternative solution:
std::vector<std::wstring> SplitString(const std::wstring & String, const std::wstring & Seperator)
{
std::vector<std::wstring> Lines;
size_t stSearchPos = 0;
size_t stFoundPos;
while (stSearchPos < String.size() - 1)
{
stFoundPos = String.find(Seperator, stSearchPos);
stFoundPos = (stFoundPos == std::string::npos) ? String.size() : stFoundPos;
Lines.push_back(String.substr(stSearchPos, stFoundPos - stSearchPos));
stSearchPos = stFoundPos + Seperator.size();
}
return Lines;
}
Test code:
std::wstring MyString(L"Part 1SEPsecond partSEPlast partSEPend");
std::vector<std::wstring> Parts = IniFile::SplitString(MyString, L"SEP");
std::wcout << L"The string: " << MyString << std::endl;
for (std::vector<std::wstring>::const_iterator it=Parts.begin(); it<Parts.end(); ++it)
{
std::wcout << *it << L"<---" << std::endl;
}
std::wcout << std::endl;
MyString = L"this,time,a,comma separated,string";
std::wcout << L"The string: " << MyString << std::endl;
Parts = IniFile::SplitString(MyString, L",");
for (std::vector<std::wstring>::const_iterator it=Parts.begin(); it<Parts.end(); ++it)
{
std::wcout << *it << L"<---" << std::endl;
}
Output of the test code:
The string: Part 1SEPsecond partSEPlast partSEPend
Part 1<---
second part<---
last part<---
end<---
The string: this,time,a,comma separated,string
this<---
time<---
a<---
comma separated<---
string<---
I have a 2 lines solution to this problem:
char sep = ' ';
std::string s="1 This is an example";
for(size_t p=0, q=0; p!=s.npos; p=q)
std::cout << s.substr(p+(p!=0), (q=s.find(sep, p+1))-p-(p!=0)) << std::endl;
Then instead of printing you can put it in a vector.
Here's another way of doing it..
void split_string(string text,vector<string>& words)
{
int i=0;
char ch;
string word;
while(ch=text[i++])
{
if (isspace(ch))
{
if (!word.empty())
{
words.push_back(word);
}
word = "";
}
else
{
word += ch;
}
}
if (!word.empty())
{
words.push_back(word);
}
}
C++20 finally blesses us with a split function. Or rather, a range adapter. Godbolt link.
#include <iostream>
#include <ranges>
#include <string_view>
namespace ranges = std::ranges;
namespace views = std::views;
using str = std::string_view;
constexpr auto view =
"Multiple words"
| views::split(' ')
| views::transform([](auto &&r) -> str {
return {
&*r.begin(),
static_cast<str::size_type>(ranges::distance(r))
};
});
auto main() -> int {
for (str &&sv : view) {
std::cout << sv << '\n';
}
}
A possible solution using Boost might be:
#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));
This approach might be even faster than the stringstream approach. And since this is a generic template function it can be used to split other types of strings (wchar, etc. or UTF-8) using all kinds of delimiters.
See the documentation for details.
The following is a much better way to do this. It can take any character, and doesn't split lines unless you want. No special libraries needed (well, besides std, but who really considers that an extra library), no pointers, no references, and it's static. Just simple plain C++.
#pragma once
#include <vector>
#include <sstream>
using namespace std;
class Helpers
{
public:
static vector<string> split(string s, char delim)
{
stringstream temp (stringstream::in | stringstream::out);
vector<string> elems(0);
if (s.size() == 0 || delim == 0)
return elems;
for(char c : s)
{
if(c == delim)
{
elems.push_back(temp.str());
temp = stringstream(stringstream::in | stringstream::out);
}
else
temp << c;
}
if (temp.str().size() > 0)
elems.push_back(temp.str());
return elems;
}
//Splits string s with a list of delimiters in delims (it's just a list, like if we wanted to
//split at the following letters, a, b, c we would make delims="abc".
static vector<string> split(string s, string delims)
{
stringstream temp (stringstream::in | stringstream::out);
vector<string> elems(0);
bool found;
if(s.size() == 0 || delims.size() == 0)
return elems;
for(char c : s)
{
found = false;
for(char d : delims)
{
if (c == d)
{
elems.push_back(temp.str());
temp = stringstream(stringstream::in | stringstream::out);
found = true;
break;
}
}
if(!found)
temp << c;
}
if(temp.str().size() > 0)
elems.push_back(temp.str());
return elems;
}
};
I wrote the following piece of code. You can specify delimiter, which can be a string. The result is similar to Java's String.split, with empty string in the result.
For example, if we call split("ABCPICKABCANYABCTWO:ABC", "ABC"), the result is as follows:
0 <len:0>
1 PICK <len:4>
2 ANY <len:3>
3 TWO: <len:4>
4 <len:0>
Code:
vector <string> split(const string& str, const string& delimiter = " ") {
vector <string> tokens;
string::size_type lastPos = 0;
string::size_type pos = str.find(delimiter, lastPos);
while (string::npos != pos) {
// Found a token, add it to the vector.
cout << str.substr(lastPos, pos - lastPos) << endl;
tokens.push_back(str.substr(lastPos, pos - lastPos));
lastPos = pos + delimiter.size();
pos = str.find(delimiter, lastPos);
}
tokens.push_back(str.substr(lastPos, str.size() - lastPos));
return tokens;
}
C++20 finally blesses us with a split function. Or rather, a range adapter. Godbolt link.
#include <iostream>
#include <ranges>
#include <string_view>
namespace ranges = std::ranges;
namespace views = std::views;
using str = std::string_view;
constexpr auto view =
"Multiple words"
| views::split(' ')
| views::transform([](auto &&r) -> str {
return {
&*r.begin(),
static_cast<str::size_type>(ranges::distance(r))
};
});
auto main() -> int {
for (str &&sv : view) {
std::cout << sv << '\n';
}
}
There is a function named strtok.
#include<string>
using namespace std;
vector<string> split(char* str,const char* delim)
{
char* saveptr;
char* token = strtok_r(str,delim,&saveptr);
vector<string> result;
while(token != NULL)
{
result.push_back(token);
token = strtok_r(NULL,delim,&saveptr);
}
return result;
}
Using std::stringstream as you have works perfectly fine, and do exactly what you wanted. If you're just looking for different way of doing things though, you can use std::find()/std::find_first_of() and std::string::substr().
Here's an example:
#include <iostream>
#include <string>
int main()
{
std::string s("Somewhere down the road");
std::string::size_type prev_pos = 0, pos = 0;
while( (pos = s.find(' ', pos)) != std::string::npos )
{
std::string substring( s.substr(prev_pos, pos-prev_pos) );
std::cout << substring << '\n';
prev_pos = ++pos;
}
std::string substring( s.substr(prev_pos, pos-prev_pos) ); // Last word
std::cout << substring << '\n';
return 0;
}
For those who need alternative in splitting string with a string delimiter, perhaps you can try my following solution.
std::vector<size_t> str_pos(const std::string &search, const std::string &target)
{
std::vector<size_t> founds;
if(!search.empty())
{
size_t start_pos = 0;
while (true)
{
size_t found_pos = target.find(search, start_pos);
if(found_pos != std::string::npos)
{
size_t found = found_pos;
founds.push_back(found);
start_pos = (found_pos + 1);
}
else
{
break;
}
}
}
return founds;
}
std::string str_sub_index(size_t begin_index, size_t end_index, const std::string &target)
{
std::string sub;
size_t size = target.length();
const char* copy = target.c_str();
for(size_t i = begin_index; i <= end_index; i++)
{
if(i >= size)
{
break;
}
else
{
char c = copy[i];
sub += c;
}
}
return sub;
}
std::vector<std::string> str_split(const std::string &delimiter, const std::string &target)
{
std::vector<std::string> splits;
if(!delimiter.empty())
{
std::vector<size_t> founds = str_pos(delimiter, target);
size_t founds_size = founds.size();
if(founds_size > 0)
{
size_t search_len = delimiter.length();
size_t begin_index = 0;
for(int i = 0; i <= founds_size; i++)
{
std::string sub;
if(i != founds_size)
{
size_t pos = founds.at(i);
sub = str_sub_index(begin_index, pos - 1, target);
begin_index = (pos + search_len);
}
else
{
sub = str_sub_index(begin_index, (target.length() - 1), target);
}
splits.push_back(sub);
}
}
}
return splits;
}
Those snippets consist of 3 function. The bad news is to use the str_split function you will need the other two functions. Yes it is a huge chunk of code. But the good news is that those additional two functions are able to work independently and sometimes can be useful too.. :)
Tested the function in main() block like this:
int main()
{
std::string s = "Hello, world! We need to make the world a better place. Because your world is also my world, and our children's world.";
std::vector<std::string> split = str_split("world", s);
for(int i = 0; i < split.size(); i++)
{
std::cout << split[i] << std::endl;
}
}
And it would produce:
Hello,
! We need to make the
a better place. Because your
is also my
, and our children's
.
I believe that's not the most efficient code, but at least it works. Hope it helps.
If you like to use boost, but want to use a whole string as delimiter (instead of single characters as in most of the previously proposed solutions), you can use the boost_split_iterator.
Example code including convenient template:
#include <iostream>
#include <vector>
#include <boost/algorithm/string.hpp>
template<typename _OutputIterator>
inline void split(
const std::string& str,
const std::string& delim,
_OutputIterator result)
{
using namespace boost::algorithm;
typedef split_iterator<std::string::const_iterator> It;
for(It iter=make_split_iterator(str, first_finder(delim, is_equal()));
iter!=It();
++iter)
{
*(result++) = boost::copy_range<std::string>(*iter);
}
}
int main(int argc, char* argv[])
{
using namespace std;
vector<string> splitted;
split("HelloFOOworldFOO!", "FOO", back_inserter(splitted));
// or directly to console, for example
split("HelloFOOworldFOO!", "FOO", ostream_iterator<string>(cout, "\n"));
return 0;
}
#include <iostream>
#include <regex>
using namespace std;
int main() {
string s = "foo bar baz";
regex e("\\s+");
regex_token_iterator<string::iterator> i(s.begin(), s.end(), e, -1);
regex_token_iterator<string::iterator> end;
while (i != end)
cout << " [" << *i++ << "]";
}
IMO, this is the closest thing to python's re.split(). See cplusplus.com for more information about regex_token_iterator. The -1 (4th argument in regex_token_iterator ctor) is the section of the sequence that is not matched, using the match as separator.
I wrote the following piece of code. You can specify delimiter, which can be a string. The result is similar to Java's String.split, with empty string in the result.
For example, if we call split("ABCPICKABCANYABCTWO:ABC", "ABC"), the result is as follows:
0 <len:0>
1 PICK <len:4>
2 ANY <len:3>
3 TWO: <len:4>
4 <len:0>
Code:
vector <string> split(const string& str, const string& delimiter = " ") {
vector <string> tokens;
string::size_type lastPos = 0;
string::size_type pos = str.find(delimiter, lastPos);
while (string::npos != pos) {
// Found a token, add it to the vector.
cout << str.substr(lastPos, pos - lastPos) << endl;
tokens.push_back(str.substr(lastPos, pos - lastPos));
lastPos = pos + delimiter.size();
pos = str.find(delimiter, lastPos);
}
tokens.push_back(str.substr(lastPos, str.size() - lastPos));
return tokens;
}
I have a very different approach from the other solutions that offers a lot of value in ways that the other solutions are variously lacking, but of course also has its own down sides. Here is the working implementation, with the example of putting <tag></tag> around words.
For a start, this problem can be solved with one loop, no additional memory, and by considering merely four logical cases. Conceptually, we're interested in boundaries. Our code should reflect that: let's iterate through the string and look at two characters at a time, bearing in mind that we have special cases at the start and end of the string.
The downside is that we have to write the implementation, which is somewhat verbose, but mostly convenient boilerplate.
The upside is that we wrote the implementation, so it is very easy to customize it to specific needs, such as distinguishing left and write word boundaries, using any set of delimiters, or handling other cases such as non-boundary or erroneous positions.
using namespace std;
#include <iostream>
#include <string>
#include <cctype>
typedef enum boundary_type_e {
E_BOUNDARY_TYPE_ERROR = -1,
E_BOUNDARY_TYPE_NONE,
E_BOUNDARY_TYPE_LEFT,
E_BOUNDARY_TYPE_RIGHT,
} boundary_type_t;
typedef struct boundary_s {
boundary_type_t type;
int pos;
} boundary_t;
bool is_delim_char(int c) {
return isspace(c); // also compare against any other chars you want to use as delimiters
}
bool is_word_char(int c) {
return ' ' <= c && c <= '~' && !is_delim_char(c);
}
boundary_t maybe_word_boundary(string str, int pos) {
int len = str.length();
if (pos < 0 || pos >= len) {
return (boundary_t){.type = E_BOUNDARY_TYPE_ERROR};
} else {
if (pos == 0 && is_word_char(str[pos])) {
// if the first character is word-y, we have a left boundary at the beginning
return (boundary_t){.type = E_BOUNDARY_TYPE_LEFT, .pos = pos};
} else if (pos == len - 1 && is_word_char(str[pos])) {
// if the last character is word-y, we have a right boundary left of the null terminator
return (boundary_t){.type = E_BOUNDARY_TYPE_RIGHT, .pos = pos + 1};
} else if (!is_word_char(str[pos]) && is_word_char(str[pos + 1])) {
// if we have a delimiter followed by a word char, we have a left boundary left of the word char
return (boundary_t){.type = E_BOUNDARY_TYPE_LEFT, .pos = pos + 1};
} else if (is_word_char(str[pos]) && !is_word_char(str[pos + 1])) {
// if we have a word char followed by a delimiter, we have a right boundary right of the word char
return (boundary_t){.type = E_BOUNDARY_TYPE_RIGHT, .pos = pos + 1};
}
return (boundary_t){.type = E_BOUNDARY_TYPE_NONE};
}
}
int main() {
string str;
getline(cin, str);
int len = str.length();
for (int i = 0; i < len; i++) {
boundary_t boundary = maybe_word_boundary(str, i);
if (boundary.type == E_BOUNDARY_TYPE_LEFT) {
// whatever
} else if (boundary.type == E_BOUNDARY_TYPE_RIGHT) {
// whatever
}
}
}
As you can see, the code is very simple to understand and fine tune, and the actual usage of the code is very short and simple. Using C++ should not stop us from writing the simplest and most readily customized code possible, even if that means not using the STL. I would think this is an instance of what Linus Torvalds might call "taste", since we have eliminated all the logic we don't need while writing in a style that naturally allows more cases to be handled when and if the need to handle them arises.
What could improve this code might be the use of enum class, accepting a function pointer to is_word_char in maybe_word_boundary instead of invoking is_word_char directly, and passing a lambda.
if you want split string by some chars you can use
#include<iostream>
#include<string>
#include<vector>
#include<iterator>
#include<sstream>
#include<string>
using namespace std;
void replaceOtherChars(string &input, vector<char> ÷rs)
{
const char divider = dividers.at(0);
int replaceIndex = 0;
vector<char>::iterator it_begin = dividers.begin()+1,
it_end= dividers.end();
for(;it_begin!=it_end;++it_begin)
{
replaceIndex = 0;
while(true)
{
replaceIndex=input.find_first_of(*it_begin,replaceIndex);
if(replaceIndex==-1)
break;
input.at(replaceIndex)=divider;
}
}
}
vector<string> split(string str, vector<char> chars, bool missEmptySpace =true )
{
vector<string> result;
const char divider = chars.at(0);
replaceOtherChars(str,chars);
stringstream stream;
stream<<str;
string temp;
while(getline(stream,temp,divider))
{
if(missEmptySpace && temp.empty())
continue;
result.push_back(temp);
}
return result;
}
int main()
{
string str ="milk, pigs.... hot-dogs ";
vector<char> arr;
arr.push_back(' '); arr.push_back(','); arr.push_back('.');
vector<string> result = split(str,arr);
vector<string>::iterator it_begin= result.begin(),
it_end= result.end();
for(;it_begin!=it_end;++it_begin)
{
cout<<*it_begin<<endl;
}
return 0;
}
#include <iostream>
#include <vector>
using namespace std;
int main() {
string str = "ABC AABCD CDDD RABC GHTTYU FR";
str += " "; //dirty hack: adding extra space to the end
vector<string> v;
for (int i=0; i<(int)str.size(); i++) {
int a, b;
a = i;
for (int j=i; j<(int)str.size(); j++) {
if (str[j] == ' ') {
b = j;
i = j;
break;
}
}
v.push_back(str.substr(a, b-a));
}
for (int i=0; i<v.size(); i++) {
cout<<v[i].size()<<" "<<v[i]<<endl;
}
return 0;
}
Here's my approach, cut and split:
string cut (string& str, const string& del)
{
string f = str;
if (in.find_first_of(del) != string::npos)
{
f = str.substr(0,str.find_first_of(del));
str = str.substr(str.find_first_of(del)+del.length());
}
return f;
}
vector<string> split (const string& in, const string& del=" ")
{
vector<string> out();
string t = in;
while (t.length() > del.length())
out.push_back(cut(t,del));
return out;
}
BTW, if there's something I can do to optimize this ..
What about this:
#include <string>
#include <vector>
using namespace std;
vector<string> split(string str, const char delim) {
vector<string> v;
string tmp;
for(string::const_iterator i; i = str.begin(); i <= str.end(); ++i) {
if(*i != delim && i != str.end()) {
tmp += *i;
} else {
v.push_back(tmp);
tmp = "";
}
}
return v;
}
// adapted from a "regular" csv parse
std::string stringIn = "my csv is 10233478 NOTseparated by commas";
std::vector<std::string> commaSeparated(1);
int commaCounter = 0;
for (int i=0; i<stringIn.size(); i++) {
if (stringIn[i] == " ") {
commaSeparated.push_back("");
commaCounter++;
} else {
commaSeparated.at(commaCounter) += stringIn[i];
}
}
in the end you will have a vector of strings with every element in the sentence separated by spaces. only non-standard resource is std::vector (but since an std::string is involved, i figured it would be acceptable).
empty strings are saved as a separate items.
This is an extension of one of the top answers. It now supports setting a max number of returned elements, N. The last bit of the string will end up in the Nth element. The MAXELEMENTS parameter is optional, if set at default 0 it will return an unlimited amount of elements. :-)
.h:
class Myneatclass {
public:
static std::vector<std::string>& split(const std::string &s, char delim, std::vector<std::string> &elems, const size_t MAXELEMENTS = 0);
static std::vector<std::string> split(const std::string &s, char delim, const size_t MAXELEMENTS = 0);
};
.cpp:
std::vector<std::string>& Myneatclass::split(const std::string &s, char delim, std::vector<std::string> &elems, const size_t MAXELEMENTS) {
std::stringstream ss(s);
std::string item;
while (std::getline(ss, item, delim)) {
elems.push_back(item);
if (MAXELEMENTS > 0 && !ss.eof() && elems.size() + 1 >= MAXELEMENTS) {
std::getline(ss, item);
elems.push_back(item);
break;
}
}
return elems;
}
std::vector<std::string> Myneatclass::split(const std::string &s, char delim, const size_t MAXELEMENTS) {
std::vector<std::string> elems;
split(s, delim, elems, MAXELEMENTS);
return elems;
}
For a ridiculously large and probably redundant version, try a lot of for loops.
string stringlist[10];
int count = 0;
for (int i = 0; i < sequence.length(); i++)
{
if (sequence[i] == ' ')
{
stringlist[count] = sequence.substr(0, i);
sequence.erase(0, i+1);
i = 0;
count++;
}
else if (i == sequence.length()-1) // Last word
{
stringlist[count] = sequence.substr(0, i+1);
}
}
It isn't pretty, but by and large (Barring punctuation and a slew of other bugs) it works!
Here's my entry:
template <typename Container, typename InputIter, typename ForwardIter>
Container
split(InputIter first, InputIter last,
ForwardIter s_first, ForwardIter s_last)
{
Container output;
while (true) {
auto pos = std::find_first_of(first, last, s_first, s_last);
output.emplace_back(first, pos);
if (pos == last) {
break;
}
first = ++pos;
}
return output;
}
template <typename Output = std::vector<std::string>,
typename Input = std::string,
typename Delims = std::string>
Output
split(const Input& input, const Delims& delims = " ")
{
using std::cbegin;
using std::cend;
return split<Output>(cbegin(input), cend(input),
cbegin(delims), cend(delims));
}
auto vec = split("Mary had a little lamb");
The first definition is an STL-style generic function taking two pair of iterators. The second is a convenience function to save you having to do all the begin()s and end()s yourself. You can also specify the output container type as a template parameter if you wanted to use a list, for example.
What makes it elegant (IMO) is that unlike most of the other answers, it's not restricted to strings but will work with any STL-compatible container. Without any change to the code above, you can say:
using vec_of_vecs_t = std::vector<std::vector<int>>;
std::vector<int> v{1, 2, 0, 3, 4, 5, 0, 7, 8, 0, 9};
auto r = split<vec_of_vecs_t>(v, std::initializer_list<int>{0, 2});
which will split the vector v into separate vectors every time a 0 or a 2 is encountered.
(There's also the added bonus that with strings, this implementation is faster than both strtok()- and getline()-based versions, at least on my system.)
Recently I had to split a camel-cased word into subwords. There are no delimiters, just upper characters.
#include <string>
#include <list>
#include <locale> // std::isupper
template<class String>
const std::list<String> split_camel_case_string(const String &s)
{
std::list<String> R;
String w;
for (String::const_iterator i = s.begin(); i < s.end(); ++i) { {
if (std::isupper(*i)) {
if (w.length()) {
R.push_back(w);
w.clear();
}
}
w += *i;
}
if (w.length())
R.push_back(w);
return R;
}
For example, this splits "AQueryTrades" into "A", "Query" and "Trades". The function works with narrow and wide strings. Because it respects the current locale it splits "RaumfahrtÜberwachungsVerordnung" into "Raumfahrt", "Überwachungs" and "Verordnung".
Note std::upper should be really passed as function template argument. Then the more generalized from of this function can split at delimiters like ",", ";" or " " too.
This is my solution to this problem:
vector<string> get_tokens(string str) {
vector<string> dt;
stringstream ss;
string tmp;
ss << str;
for (size_t i; !ss.eof(); ++i) {
ss >> tmp;
dt.push_back(tmp);
}
return dt;
}
This function returns a vector of strings.
I've rolled my own using strtok and used boost to split a string. The best method I have found is the C++ String Toolkit Library. It is incredibly flexible and fast.
#include <iostream>
#include <vector>
#include <string>
#include <strtk.hpp>
const char *whitespace = " \t\r\n\f";
const char *whitespace_and_punctuation = " \t\r\n\f;,=";
int main()
{
{ // normal parsing of a string into a vector of strings
std::string s("Somewhere down the road");
std::vector<std::string> result;
if( strtk::parse( s, whitespace, result ) )
{
for(size_t i = 0; i < result.size(); ++i )
std::cout << result[i] << std::endl;
}
}
{ // parsing a string into a vector of floats with other separators
// besides spaces
std::string s("3.0, 3.14; 4.0");
std::vector<float> values;
if( strtk::parse( s, whitespace_and_punctuation, values ) )
{
for(size_t i = 0; i < values.size(); ++i )
std::cout << values[i] << std::endl;
}
}
{ // parsing a string into specific variables
std::string s("angle = 45; radius = 9.9");
std::string w1, w2;
float v1, v2;
if( strtk::parse( s, whitespace_and_punctuation, w1, v1, w2, v2) )
{
std::cout << "word " << w1 << ", value " << v1 << std::endl;
std::cout << "word " << w2 << ", value " << v2 << std::endl;
}
}
return 0;
}
The toolkit has much more flexibility than this simple example shows but its utility in parsing a string into useful elements is incredible.
This is similar to Stack Overflow question How do I tokenize a string in C++?.
#include <iostream>
#include <string>
#include <boost/tokenizer.hpp>
using namespace std;
using namespace boost;
int main(int argc, char** argv)
{
string text = "token test\tstring";
char_separator<char> sep(" \t");
tokenizer<char_separator<char>> tokens(text, sep);
for (const string& t : tokens)
{
cout << t << "." << endl;
}
}
The STL does not have such a method available already.
However, you can either use C's strtok() function by using the std::string::c_str() member, or you can write your own. Here is a code sample I found after a quick Google search ("STL string split"):
void Tokenize(const string& str,
vector<string>& tokens,
const string& delimiters = " ")
{
// Skip delimiters at beginning.
string::size_type lastPos = str.find_first_not_of(delimiters, 0);
// Find first "non-delimiter".
string::size_type pos = str.find_first_of(delimiters, lastPos);
while (string::npos != pos || string::npos != lastPos)
{
// Found a token, add it to the vector.
tokens.push_back(str.substr(lastPos, pos - lastPos));
// Skip delimiters. Note the "not_of"
lastPos = str.find_first_not_of(delimiters, pos);
// Find next "non-delimiter"
pos = str.find_first_of(delimiters, lastPos);
}
}
Taken from: http://oopweb.com/CPP/Documents/CPPHOWTO/Volume/C++Programming-HOWTO-7.html
If you have questions about the code sample, leave a comment and I will explain.
And just because it does not implement a typedef called iterator or overload the << operator does not mean it is bad code. I use C functions quite frequently. For example, printf and scanf both are faster than std::cin and std::cout (significantly), the fopen syntax is a lot more friendly for binary types, and they also tend to produce smaller EXEs.
Don't get sold on this "Elegance over performance" deal.
For those who need alternative in splitting string with a string delimiter, perhaps you can try my following solution.
std::vector<size_t> str_pos(const std::string &search, const std::string &target)
{
std::vector<size_t> founds;
if(!search.empty())
{
size_t start_pos = 0;
while (true)
{
size_t found_pos = target.find(search, start_pos);
if(found_pos != std::string::npos)
{
size_t found = found_pos;
founds.push_back(found);
start_pos = (found_pos + 1);
}
else
{
break;
}
}
}
return founds;
}
std::string str_sub_index(size_t begin_index, size_t end_index, const std::string &target)
{
std::string sub;
size_t size = target.length();
const char* copy = target.c_str();
for(size_t i = begin_index; i <= end_index; i++)
{
if(i >= size)
{
break;
}
else
{
char c = copy[i];
sub += c;
}
}
return sub;
}
std::vector<std::string> str_split(const std::string &delimiter, const std::string &target)
{
std::vector<std::string> splits;
if(!delimiter.empty())
{
std::vector<size_t> founds = str_pos(delimiter, target);
size_t founds_size = founds.size();
if(founds_size > 0)
{
size_t search_len = delimiter.length();
size_t begin_index = 0;
for(int i = 0; i <= founds_size; i++)
{
std::string sub;
if(i != founds_size)
{
size_t pos = founds.at(i);
sub = str_sub_index(begin_index, pos - 1, target);
begin_index = (pos + search_len);
}
else
{
sub = str_sub_index(begin_index, (target.length() - 1), target);
}
splits.push_back(sub);
}
}
}
return splits;
}
Those snippets consist of 3 function. The bad news is to use the str_split function you will need the other two functions. Yes it is a huge chunk of code. But the good news is that those additional two functions are able to work independently and sometimes can be useful too.. :)
Tested the function in main() block like this:
int main()
{
std::string s = "Hello, world! We need to make the world a better place. Because your world is also my world, and our children's world.";
std::vector<std::string> split = str_split("world", s);
for(int i = 0; i < split.size(); i++)
{
std::cout << split[i] << std::endl;
}
}
And it would produce:
Hello,
! We need to make the
a better place. Because your
is also my
, and our children's
.
I believe that's not the most efficient code, but at least it works. Hope it helps.
I like the following because it puts the results into a vector, supports a string as a delim and gives control over keeping empty values. But, it doesn't look as good then.
#include <ostream>
#include <string>
#include <vector>
#include <algorithm>
#include <iterator>
using namespace std;
vector<string> split(const string& s, const string& delim, const bool keep_empty = true) {
vector<string> result;
if (delim.empty()) {
result.push_back(s);
return result;
}
string::const_iterator substart = s.begin(), subend;
while (true) {
subend = search(substart, s.end(), delim.begin(), delim.end());
string temp(substart, subend);
if (keep_empty || !temp.empty()) {
result.push_back(temp);
}
if (subend == s.end()) {
break;
}
substart = subend + delim.size();
}
return result;
}
int main() {
const vector<string> words = split("So close no matter how far", " ");
copy(words.begin(), words.end(), ostream_iterator<string>(cout, "\n"));
}
Of course, Boost has a split() that works partially like that. And, if by 'white-space', you really do mean any type of white-space, using Boost's split with is_any_of() works great.
I use this to split string by a delimiter. The first puts the results in a pre-constructed vector, the second returns a new vector.
#include <string>
#include <sstream>
#include <vector>
#include <iterator>
template <typename Out>
void split(const std::string &s, char delim, Out result) {
std::istringstream iss(s);
std::string item;
while (std::getline(iss, item, delim)) {
*result++ = item;
}
}
std::vector<std::string> split(const std::string &s, char delim) {
std::vector<std::string> elems;
split(s, delim, std::back_inserter(elems));
return elems;
}
Note that this solution does not skip empty tokens, so the following will find 4 items, one of which is empty:
std::vector<std::string> x = split("one:two::three", ':');
Here's my take on this. I had to process the input string word by word, which could have been done by using space to count words but I felt it would be tedious and I should split the words into vectors.
#include<iostream>
#include<vector>
#include<string>
#include<stdio.h>
using namespace std;
int main()
{
char x = '\0';
string s = "";
vector<string> q;
x = getchar();
while(x != '\n')
{
if(x == ' ')
{
q.push_back(s);
s = "";
x = getchar();
continue;
}
s = s + x;
x = getchar();
}
q.push_back(s);
for(int i = 0; i<q.size(); i++)
cout<<q[i]<<" ";
return 0;
}
Thank you @Jairo Abdiel Toribio Cisneros. It works for me but your function return some empty element. So for return without empty I have edited with the following:
std::vector<std::string> split(std::string str, const char* delim) {
std::vector<std::string> v;
std::string tmp;
for(std::string::const_iterator i = str.begin(); i <= str.end(); ++i) {
if(*i != *delim && i != str.end()) {
tmp += *i;
} else {
if (tmp.length() > 0) {
v.push_back(tmp);
}
tmp = "";
}
}
return v;
}
Using:
std::string s = "one:two::three";
std::string delim = ":";
std::vector<std::string> vv = split(s, delim.c_str());
Here's my take on this. I had to process the input string word by word, which could have been done by using space to count words but I felt it would be tedious and I should split the words into vectors.
#include<iostream>
#include<vector>
#include<string>
#include<stdio.h>
using namespace std;
int main()
{
char x = '\0';
string s = "";
vector<string> q;
x = getchar();
while(x != '\n')
{
if(x == ' ')
{
q.push_back(s);
s = "";
x = getchar();
continue;
}
s = s + x;
x = getchar();
}
q.push_back(s);
for(int i = 0; i<q.size(); i++)
cout<<q[i]<<" ";
return 0;
}
I made this because I needed an easy way to split strings and c-based strings... Hopefully someone else can find it useful as well. Also it doesn't rely on tokens and you can use fields as delimiters, which is another key I needed.
I'm sure there's improvements that can be made to even further improve its elegance and please do by all means
StringSplitter.hpp:
#include <vector>
#include <iostream>
#include <string.h>
using namespace std;
class StringSplit
{
private:
void copy_fragment(char*, char*, char*);
void copy_fragment(char*, char*, char);
bool match_fragment(char*, char*, int);
int untilnextdelim(char*, char);
int untilnextdelim(char*, char*);
void assimilate(char*, char);
void assimilate(char*, char*);
bool string_contains(char*, char*);
long calc_string_size(char*);
void copy_string(char*, char*);
public:
vector<char*> split_cstr(char);
vector<char*> split_cstr(char*);
vector<string> split_string(char);
vector<string> split_string(char*);
char* String;
bool do_string;
bool keep_empty;
vector<char*> Container;
vector<string> ContainerS;
StringSplit(char * in)
{
String = in;
}
StringSplit(string in)
{
size_t len = calc_string_size((char*)in.c_str());
String = new char[len + 1];
memset(String, 0, len + 1);
copy_string(String, (char*)in.c_str());
do_string = true;
}
~StringSplit()
{
for (int i = 0; i < Container.size(); i++)
{
if (Container[i] != NULL)
{
delete[] Container[i];
}
}
if (do_string)
{
delete[] String;
}
}
};
StringSplitter.cpp:
#include <string.h>
#include <iostream>
#include <vector>
#include "StringSplit.hpp"
using namespace std;
void StringSplit::assimilate(char*src, char delim)
{
int until = untilnextdelim(src, delim);
if (until > 0)
{
char * temp = new char[until + 1];
memset(temp, 0, until + 1);
copy_fragment(temp, src, delim);
if (keep_empty || *temp != 0)
{
if (!do_string)
{
Container.push_back(temp);
}
else
{
string x = temp;
ContainerS.push_back(x);
}
}
else
{
delete[] temp;
}
}
}
void StringSplit::assimilate(char*src, char* delim)
{
int until = untilnextdelim(src, delim);
if (until > 0)
{
char * temp = new char[until + 1];
memset(temp, 0, until + 1);
copy_fragment(temp, src, delim);
if (keep_empty || *temp != 0)
{
if (!do_string)
{
Container.push_back(temp);
}
else
{
string x = temp;
ContainerS.push_back(x);
}
}
else
{
delete[] temp;
}
}
}
long StringSplit::calc_string_size(char* _in)
{
long i = 0;
while (*_in++)
{
i++;
}
return i;
}
bool StringSplit::string_contains(char* haystack, char* needle)
{
size_t len = calc_string_size(needle);
size_t lenh = calc_string_size(haystack);
while (lenh--)
{
if (match_fragment(haystack + lenh, needle, len))
{
return true;
}
}
return false;
}
bool StringSplit::match_fragment(char* _src, char* cmp, int len)
{
while (len--)
{
if (*(_src + len) != *(cmp + len))
{
return false;
}
}
return true;
}
int StringSplit::untilnextdelim(char* _in, char delim)
{
size_t len = calc_string_size(_in);
if (*_in == delim)
{
_in += 1;
return len - 1;
}
int c = 0;
while (*(_in + c) != delim && c < len)
{
c++;
}
return c;
}
int StringSplit::untilnextdelim(char* _in, char* delim)
{
int s = calc_string_size(delim);
int c = 1 + s;
if (!string_contains(_in, delim))
{
return calc_string_size(_in);
}
else if (match_fragment(_in, delim, s))
{
_in += s;
return calc_string_size(_in);
}
while (!match_fragment(_in + c, delim, s))
{
c++;
}
return c;
}
void StringSplit::copy_fragment(char* dest, char* src, char delim)
{
if (*src == delim)
{
src++;
}
int c = 0;
while (*(src + c) != delim && *(src + c))
{
*(dest + c) = *(src + c);
c++;
}
*(dest + c) = 0;
}
void StringSplit::copy_string(char* dest, char* src)
{
int i = 0;
while (*(src + i))
{
*(dest + i) = *(src + i);
i++;
}
}
void StringSplit::copy_fragment(char* dest, char* src, char* delim)
{
size_t len = calc_string_size(delim);
size_t lens = calc_string_size(src);
if (match_fragment(src, delim, len))
{
src += len;
lens -= len;
}
int c = 0;
while (!match_fragment(src + c, delim, len) && (c < lens))
{
*(dest + c) = *(src + c);
c++;
}
*(dest + c) = 0;
}
vector<char*> StringSplit::split_cstr(char Delimiter)
{
int i = 0;
while (*String)
{
if (*String != Delimiter && i == 0)
{
assimilate(String, Delimiter);
}
if (*String == Delimiter)
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return Container;
}
vector<string> StringSplit::split_string(char Delimiter)
{
do_string = true;
int i = 0;
while (*String)
{
if (*String != Delimiter && i == 0)
{
assimilate(String, Delimiter);
}
if (*String == Delimiter)
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return ContainerS;
}
vector<char*> StringSplit::split_cstr(char* Delimiter)
{
int i = 0;
size_t LenDelim = calc_string_size(Delimiter);
while(*String)
{
if (!match_fragment(String, Delimiter, LenDelim) && i == 0)
{
assimilate(String, Delimiter);
}
if (match_fragment(String, Delimiter, LenDelim))
{
assimilate(String,Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return Container;
}
vector<string> StringSplit::split_string(char* Delimiter)
{
do_string = true;
int i = 0;
size_t LenDelim = calc_string_size(Delimiter);
while (*String)
{
if (!match_fragment(String, Delimiter, LenDelim) && i == 0)
{
assimilate(String, Delimiter);
}
if (match_fragment(String, Delimiter, LenDelim))
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return ContainerS;
}
Examples:
int main(int argc, char*argv[])
{
StringSplit ss = "This:CUT:is:CUT:an:CUT:example:CUT:cstring";
vector<char*> Split = ss.split_cstr(":CUT:");
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
Will output:
This
is
an
example
cstring
int main(int argc, char*argv[])
{
StringSplit ss = "This:is:an:example:cstring";
vector<char*> Split = ss.split_cstr(':');
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
int main(int argc, char*argv[])
{
string mystring = "This[SPLIT]is[SPLIT]an[SPLIT]example[SPLIT]string";
StringSplit ss = mystring;
vector<string> Split = ss.split_string("[SPLIT]");
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
int main(int argc, char*argv[])
{
string mystring = "This|is|an|example|string";
StringSplit ss = mystring;
vector<string> Split = ss.split_string('|');
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
To keep empty entries (by default empties will be excluded):
StringSplit ss = mystring;
ss.keep_empty = true;
vector<string> Split = ss.split_string(":DELIM:");
The goal was to make it similar to C#'s Split() method where splitting a string is as easy as:
String[] Split =
"Hey:cut:what's:cut:your:cut:name?".Split(new[]{":cut:"}, StringSplitOptions.None);
foreach(String X in Split)
{
Console.Write(X);
}
I hope someone else can find this as useful as I do.
Thank you @Jairo Abdiel Toribio Cisneros. It works for me but your function return some empty element. So for return without empty I have edited with the following:
std::vector<std::string> split(std::string str, const char* delim) {
std::vector<std::string> v;
std::string tmp;
for(std::string::const_iterator i = str.begin(); i <= str.end(); ++i) {
if(*i != *delim && i != str.end()) {
tmp += *i;
} else {
if (tmp.length() > 0) {
v.push_back(tmp);
}
tmp = "";
}
}
return v;
}
Using:
std::string s = "one:two::three";
std::string delim = ":";
std::vector<std::string> vv = split(s, delim.c_str());
I believe no one has posted this solution yet. Instead of using delimiters directly, it basically does the same as boost::split(), i.e., it allows you to pass a predicate that returns true if a char is a delimiter, and false otherwise. I think this gives the programmer a lot more control, and the great thing is you don't need boost.
template <class Container, class String, class Predicate>
void split(Container& output, const String& input,
const Predicate& pred, bool trimEmpty = false) {
auto it = begin(input);
auto itLast = it;
while (it = find_if(it, end(input), pred), it != end(input)) {
if (not (trimEmpty and it == itLast)) {
output.emplace_back(itLast, it);
}
++it;
itLast = it;
}
}
Then you can use it like this:
struct Delim {
bool operator()(char c) {
return not isalpha(c);
}
};
int main() {
string s("#include<iostream>\n"
"int main() { std::cout << \"Hello world!\" << std::endl; }");
vector<string> v;
split(v, s, Delim(), true);
/* Which is also the same as */
split(v, s, [](char c) { return not isalpha(c); }, true);
for (const auto& i : v) {
cout << i << endl;
}
}
For a ridiculously large and probably redundant version, try a lot of for loops.
string stringlist[10];
int count = 0;
for (int i = 0; i < sequence.length(); i++)
{
if (sequence[i] == ' ')
{
stringlist[count] = sequence.substr(0, i);
sequence.erase(0, i+1);
i = 0;
count++;
}
else if (i == sequence.length()-1) // Last word
{
stringlist[count] = sequence.substr(0, i+1);
}
}
It isn't pretty, but by and large (Barring punctuation and a slew of other bugs) it works!
I've rolled my own using strtok and used boost to split a string. The best method I have found is the C++ String Toolkit Library. It is incredibly flexible and fast.
#include <iostream>
#include <vector>
#include <string>
#include <strtk.hpp>
const char *whitespace = " \t\r\n\f";
const char *whitespace_and_punctuation = " \t\r\n\f;,=";
int main()
{
{ // normal parsing of a string into a vector of strings
std::string s("Somewhere down the road");
std::vector<std::string> result;
if( strtk::parse( s, whitespace, result ) )
{
for(size_t i = 0; i < result.size(); ++i )
std::cout << result[i] << std::endl;
}
}
{ // parsing a string into a vector of floats with other separators
// besides spaces
std::string s("3.0, 3.14; 4.0");
std::vector<float> values;
if( strtk::parse( s, whitespace_and_punctuation, values ) )
{
for(size_t i = 0; i < values.size(); ++i )
std::cout << values[i] << std::endl;
}
}
{ // parsing a string into specific variables
std::string s("angle = 45; radius = 9.9");
std::string w1, w2;
float v1, v2;
if( strtk::parse( s, whitespace_and_punctuation, w1, v1, w2, v2) )
{
std::cout << "word " << w1 << ", value " << v1 << std::endl;
std::cout << "word " << w2 << ", value " << v2 << std::endl;
}
}
return 0;
}
The toolkit has much more flexibility than this simple example shows but its utility in parsing a string into useful elements is incredible.
Here is my version
#include <vector>
inline std::vector<std::string> Split(const std::string &str, const std::string &delim = " ")
{
std::vector<std::string> tokens;
if (str.size() > 0)
{
if (delim.size() > 0)
{
std::string::size_type currPos = 0, prevPos = 0;
while ((currPos = str.find(delim, prevPos)) != std::string::npos)
{
std::string item = str.substr(prevPos, currPos - prevPos);
if (item.size() > 0)
{
tokens.push_back(item);
}
prevPos = currPos + 1;
}
tokens.push_back(str.substr(prevPos));
}
else
{
tokens.push_back(str);
}
}
return tokens;
}
It works with multi-character delimiters. It prevents empty tokens to get in your results. It uses a single header. It returns the string as one single token when you provide no delimiter. It also returns an empty result if the string is empty. It is unfortunately inefficient because of the huge std::vector copy UNLESS you are compiling using C++11, which should be using the move schematic. In C++11, this code should be fast.
Yes, I looked through all 30 examples.
I couldn't find a version of split that works for multi-char delimiters, so here's mine:
#include <string>
#include <vector>
using namespace std;
vector<string> split(const string &str, const string &delim)
{
const auto delim_pos = str.find(delim);
if (delim_pos == string::npos)
return {str};
vector<string> ret{str.substr(0, delim_pos)};
auto tail = split(str.substr(delim_pos + delim.size(), string::npos), delim);
ret.insert(ret.end(), tail.begin(), tail.end());
return ret;
}
Probably not the most efficient of implementations, but it's a very straightforward recursive solution, using only <string> and <vector>.
Ah, it's written in C++11, but there's nothing special about this code, so you could easily adapt it to C++98.
Get Boost ! : -)
#include <boost/algorithm/string/split.hpp>
#include <boost/algorithm/string.hpp>
#include <iostream>
#include <vector>
using namespace std;
using namespace boost;
int main(int argc, char**argv) {
typedef vector < string > list_type;
list_type list;
string line;
line = "Somewhere down the road";
split(list, line, is_any_of(" "));
for(int i = 0; i < list.size(); i++)
{
cout << list[i] << endl;
}
return 0;
}
This example gives the output -
Somewhere
down
the
road
No Boost, no string streams, just the standard C library cooperating together with std::string and std::list: C library functions for easy analysis, C++ data types for easy memory management.
Whitespace is considered to be any combination of newlines, tabs and spaces. The set of whitespace characters is established by the wschars variable.
#include <string>
#include <list>
#include <iostream>
#include <cstring>
using namespace std;
const char *wschars = "\t\n ";
list<string> split(const string &str)
{
const char *cstr = str.c_str();
list<string> out;
while (*cstr) { // while remaining string not empty
size_t toklen;
cstr += strspn(cstr, wschars); // skip leading whitespace
toklen = strcspn(cstr, wschars); // figure out token length
if (toklen) // if we have a token, add to list
out.push_back(string(cstr, toklen));
cstr += toklen; // skip over token
}
// ran out of string; return list
return out;
}
int main(int argc, char **argv)
{
list<string> li = split(argv[1]);
for (list<string>::iterator i = li.begin(); i != li.end(); i++)
cout << "{" << *i << "}" << endl;
return 0;
}
Run:
$ ./split ""
$ ./split "a"
{a}
$ ./split " a "
{a}
$ ./split " a b"
{a}
{b}
$ ./split " a b c"
{a}
{b}
{c}
$ ./split " a b c d "
{a}
{b}
{c}
{d}
Tail-recursive version of split (itself split into two functions). All destructive manipulation of variables is gone, except for the pushing of strings into the list!
void split_rec(const char *cstr, list<string> &li)
{
if (*cstr) {
const size_t leadsp = strspn(cstr, wschars);
const size_t toklen = strcspn(cstr + leadsp, wschars);
if (toklen)
li.push_back(string(cstr + leadsp, toklen));
split_rec(cstr + leadsp + toklen, li);
}
}
list<string> split(const string &str)
{
list<string> out;
split_rec(str.c_str(), out);
return out;
}
Loop on getline with ' ' as the token.
I like the following because it puts the results into a vector, supports a string as a delim and gives control over keeping empty values. But, it doesn't look as good then.
#include <ostream>
#include <string>
#include <vector>
#include <algorithm>
#include <iterator>
using namespace std;
vector<string> split(const string& s, const string& delim, const bool keep_empty = true) {
vector<string> result;
if (delim.empty()) {
result.push_back(s);
return result;
}
string::const_iterator substart = s.begin(), subend;
while (true) {
subend = search(substart, s.end(), delim.begin(), delim.end());
string temp(substart, subend);
if (keep_empty || !temp.empty()) {
result.push_back(temp);
}
if (subend == s.end()) {
break;
}
substart = subend + delim.size();
}
return result;
}
int main() {
const vector<string> words = split("So close no matter how far", " ");
copy(words.begin(), words.end(), ostream_iterator<string>(cout, "\n"));
}
Of course, Boost has a split() that works partially like that. And, if by 'white-space', you really do mean any type of white-space, using Boost's split with is_any_of() works great.
This is similar to Stack Overflow question How do I tokenize a string in C++?.
#include <iostream>
#include <string>
#include <boost/tokenizer.hpp>
using namespace std;
using namespace boost;
int main(int argc, char** argv)
{
string text = "token test\tstring";
char_separator<char> sep(" \t");
tokenizer<char_separator<char>> tokens(text, sep);
for (const string& t : tokens)
{
cout << t << "." << endl;
}
}
So far I used the one in Boost, but I needed something that doesn't depends on it, so I came to this:
static void Split(std::vector<std::string>& lst, const std::string& input, const std::string& separators, bool remove_empty = true)
{
std::ostringstream word;
for (size_t n = 0; n < input.size(); ++n)
{
if (std::string::npos == separators.find(input[n]))
word << input[n];
else
{
if (!word.str().empty() || !remove_empty)
lst.push_back(word.str());
word.str("");
}
}
if (!word.str().empty() || !remove_empty)
lst.push_back(word.str());
}
A good point is that in separators you can pass more than one character.
This is similar to Stack Overflow question How do I tokenize a string in C++?.
#include <iostream>
#include <string>
#include <boost/tokenizer.hpp>
using namespace std;
using namespace boost;
int main(int argc, char** argv)
{
string text = "token test\tstring";
char_separator<char> sep(" \t");
tokenizer<char_separator<char>> tokens(text, sep);
for (const string& t : tokens)
{
cout << t << "." << endl;
}
}
This is my versión taken the source of Kev:
#include <string>
#include <vector>
void split(vector<string> &result, string str, char delim ) {
string tmp;
string::iterator i;
result.clear();
for(i = str.begin(); i <= str.end(); ++i) {
if((const char)*i != delim && i != str.end()) {
tmp += *i;
} else {
result.push_back(tmp);
tmp = "";
}
}
}
After, call the function and do something with it:
vector<string> hosts;
split(hosts, "192.168.1.2,192.168.1.3", ',');
for( size_t i = 0; i < hosts.size(); i++){
cout << "Connecting host : " << hosts.at(i) << "..." << endl;
}
Recently I had to split a camel-cased word into subwords. There are no delimiters, just upper characters.
#include <string>
#include <list>
#include <locale> // std::isupper
template<class String>
const std::list<String> split_camel_case_string(const String &s)
{
std::list<String> R;
String w;
for (String::const_iterator i = s.begin(); i < s.end(); ++i) { {
if (std::isupper(*i)) {
if (w.length()) {
R.push_back(w);
w.clear();
}
}
w += *i;
}
if (w.length())
R.push_back(w);
return R;
}
For example, this splits "AQueryTrades" into "A", "Query" and "Trades". The function works with narrow and wide strings. Because it respects the current locale it splits "RaumfahrtÜberwachungsVerordnung" into "Raumfahrt", "Überwachungs" and "Verordnung".
Note std::upper should be really passed as function template argument. Then the more generalized from of this function can split at delimiters like ",", ";" or " " too.
I have a very different approach from the other solutions that offers a lot of value in ways that the other solutions are variously lacking, but of course also has its own down sides. Here is the working implementation, with the example of putting <tag></tag> around words.
For a start, this problem can be solved with one loop, no additional memory, and by considering merely four logical cases. Conceptually, we're interested in boundaries. Our code should reflect that: let's iterate through the string and look at two characters at a time, bearing in mind that we have special cases at the start and end of the string.
The downside is that we have to write the implementation, which is somewhat verbose, but mostly convenient boilerplate.
The upside is that we wrote the implementation, so it is very easy to customize it to specific needs, such as distinguishing left and write word boundaries, using any set of delimiters, or handling other cases such as non-boundary or erroneous positions.
using namespace std;
#include <iostream>
#include <string>
#include <cctype>
typedef enum boundary_type_e {
E_BOUNDARY_TYPE_ERROR = -1,
E_BOUNDARY_TYPE_NONE,
E_BOUNDARY_TYPE_LEFT,
E_BOUNDARY_TYPE_RIGHT,
} boundary_type_t;
typedef struct boundary_s {
boundary_type_t type;
int pos;
} boundary_t;
bool is_delim_char(int c) {
return isspace(c); // also compare against any other chars you want to use as delimiters
}
bool is_word_char(int c) {
return ' ' <= c && c <= '~' && !is_delim_char(c);
}
boundary_t maybe_word_boundary(string str, int pos) {
int len = str.length();
if (pos < 0 || pos >= len) {
return (boundary_t){.type = E_BOUNDARY_TYPE_ERROR};
} else {
if (pos == 0 && is_word_char(str[pos])) {
// if the first character is word-y, we have a left boundary at the beginning
return (boundary_t){.type = E_BOUNDARY_TYPE_LEFT, .pos = pos};
} else if (pos == len - 1 && is_word_char(str[pos])) {
// if the last character is word-y, we have a right boundary left of the null terminator
return (boundary_t){.type = E_BOUNDARY_TYPE_RIGHT, .pos = pos + 1};
} else if (!is_word_char(str[pos]) && is_word_char(str[pos + 1])) {
// if we have a delimiter followed by a word char, we have a left boundary left of the word char
return (boundary_t){.type = E_BOUNDARY_TYPE_LEFT, .pos = pos + 1};
} else if (is_word_char(str[pos]) && !is_word_char(str[pos + 1])) {
// if we have a word char followed by a delimiter, we have a right boundary right of the word char
return (boundary_t){.type = E_BOUNDARY_TYPE_RIGHT, .pos = pos + 1};
}
return (boundary_t){.type = E_BOUNDARY_TYPE_NONE};
}
}
int main() {
string str;
getline(cin, str);
int len = str.length();
for (int i = 0; i < len; i++) {
boundary_t boundary = maybe_word_boundary(str, i);
if (boundary.type == E_BOUNDARY_TYPE_LEFT) {
// whatever
} else if (boundary.type == E_BOUNDARY_TYPE_RIGHT) {
// whatever
}
}
}
As you can see, the code is very simple to understand and fine tune, and the actual usage of the code is very short and simple. Using C++ should not stop us from writing the simplest and most readily customized code possible, even if that means not using the STL. I would think this is an instance of what Linus Torvalds might call "taste", since we have eliminated all the logic we don't need while writing in a style that naturally allows more cases to be handled when and if the need to handle them arises.
What could improve this code might be the use of enum class, accepting a function pointer to is_word_char in maybe_word_boundary instead of invoking is_word_char directly, and passing a lambda.
When dealing with whitespace as separator, the obvious answer of using std::istream_iterator<T> is already given and voted up a lot. Of course, elements may not be separated by whitespace but by some separator instead. I didn't spot any answer which just redefines the meaning of whitespace to be said separator and then uses the conventional approach.
The way to change what streams consider whitespace, you'd simply change the stream's std::locale using (std::istream::imbue()) with a std::ctype<char> facet with its own definition of what whitespace means (it can be done for std::ctype<wchar_t>, too, but its is actually slightly different because std::ctype<char> is table-driven while std::ctype<wchar_t> is driven by virtual functions).
#include <iostream>
#include <algorithm>
#include <iterator>
#include <sstream>
#include <locale>
struct whitespace_mask {
std::ctype_base::mask mask_table[std::ctype<char>::table_size];
whitespace_mask(std::string const& spaces) {
std::ctype_base::mask* table = this->mask_table;
std::ctype_base::mask const* tab
= std::use_facet<std::ctype<char>>(std::locale()).table();
for (std::size_t i(0); i != std::ctype<char>::table_size; ++i) {
table[i] = tab[i] & ~std::ctype_base::space;
}
std::for_each(spaces.begin(), spaces.end(), [=](unsigned char c) {
table[c] |= std::ctype_base::space;
});
}
};
class whitespace_facet
: private whitespace_mask
, public std::ctype<char> {
public:
whitespace_facet(std::string const& spaces)
: whitespace_mask(spaces)
, std::ctype<char>(this->mask_table) {
}
};
struct whitespace {
std::string spaces;
whitespace(std::string const& spaces): spaces(spaces) {}
};
std::istream& operator>>(std::istream& in, whitespace const& ws) {
std::locale loc(in.getloc(), new whitespace_facet(ws.spaces));
in.imbue(loc);
return in;
}
// everything above would probably go into a utility library...
int main() {
std::istringstream in("a, b, c, d, e");
std::copy(std::istream_iterator<std::string>(in >> whitespace(", ")),
std::istream_iterator<std::string>(),
std::ostream_iterator<std::string>(std::cout, "\n"));
std::istringstream pipes("a b c| d |e e");
std::copy(std::istream_iterator<std::string>(pipes >> whitespace("|")),
std::istream_iterator<std::string>(),
std::ostream_iterator<std::string>(std::cout, "\n"));
}
Most of the code is for packaging up a general purpose tool providing soft delimiters: multiple delimiters in a row are merged. There is no way to produce an empty sequence. When different delimiters are needed within a stream, you'd probably use differently set up streams using a shared stream buffer:
void f(std::istream& in) {
std::istream pipes(in.rdbuf());
pipes >> whitespace("|");
std::istream comma(in.rdbuf());
comma >> whitespace(",");
std::string s0, s1;
if (pipes >> s0 >> std::ws // read up to first pipe and ignore sequence of pipes
&& comma >> s1 >> std::ws) { // read up to first comma and ignore commas
// ...
}
}
This is my favorite way to iterate through a string. You can do whatever you want per word.
string line = "a line of text to iterate through";
string word;
istringstream iss(line, istringstream::in);
while( iss >> word )
{
// Do something on `word` here...
}
Here's a simple solution that uses only the standard regex library
#include <regex>
#include <string>
#include <vector>
std::vector<string> Tokenize( const string str, const std::regex regex )
{
using namespace std;
std::vector<string> result;
sregex_token_iterator it( str.begin(), str.end(), regex, -1 );
sregex_token_iterator reg_end;
for ( ; it != reg_end; ++it ) {
if ( !it->str().empty() ) //token could be empty:check
result.emplace_back( it->str() );
}
return result;
}
The regex argument allows checking for multiple arguments (spaces, commas, etc.)
I usually only check to split on spaces and commas, so I also have this default function:
std::vector<string> TokenizeDefault( const string str )
{
using namespace std;
regex re( "[\\s,]+" );
return Tokenize( str, re );
}
The "[\\s,]+" checks for spaces (\\s) and commas (,).
Note, if you want to split wstring instead of string,
std::regex to std::wregexsregex_token_iterator to wsregex_token_iteratorNote, you might also want to take the string argument by reference, depending on your compiler.
We can use strtok in c++ ,
#include <iostream>
#include <cstring>
using namespace std;
int main()
{
char str[]="Mickey M;12034;911416313;M;01a;9001;NULL;0;13;12;0;CPP,C;MSC,3D;FEND,BEND,SEC;";
char *pch = strtok (str,";,");
while (pch != NULL)
{
cout<<pch<<"\n";
pch = strtok (NULL, ";,");
}
return 0;
}
For a ridiculously large and probably redundant version, try a lot of for loops.
string stringlist[10];
int count = 0;
for (int i = 0; i < sequence.length(); i++)
{
if (sequence[i] == ' ')
{
stringlist[count] = sequence.substr(0, i);
sequence.erase(0, i+1);
i = 0;
count++;
}
else if (i == sequence.length()-1) // Last word
{
stringlist[count] = sequence.substr(0, i+1);
}
}
It isn't pretty, but by and large (Barring punctuation and a slew of other bugs) it works!
This is my favorite way to iterate through a string. You can do whatever you want per word.
string line = "a line of text to iterate through";
string word;
istringstream iss(line, istringstream::in);
while( iss >> word )
{
// Do something on `word` here...
}
I use this to split string by a delimiter. The first puts the results in a pre-constructed vector, the second returns a new vector.
#include <string>
#include <sstream>
#include <vector>
#include <iterator>
template <typename Out>
void split(const std::string &s, char delim, Out result) {
std::istringstream iss(s);
std::string item;
while (std::getline(iss, item, delim)) {
*result++ = item;
}
}
std::vector<std::string> split(const std::string &s, char delim) {
std::vector<std::string> elems;
split(s, delim, std::back_inserter(elems));
return elems;
}
Note that this solution does not skip empty tokens, so the following will find 4 items, one of which is empty:
std::vector<std::string> x = split("one:two::three", ':');
I use the following code:
namespace Core
{
typedef std::wstring String;
void SplitString(const Core::String& input, const Core::String& splitter, std::list<Core::String>& output)
{
if (splitter.empty())
{
throw std::invalid_argument(); // for example
}
std::list<Core::String> lines;
Core::String::size_type offset = 0;
for (;;)
{
Core::String::size_type splitterPos = input.find(splitter, offset);
if (splitterPos != Core::String::npos)
{
lines.push_back(input.substr(offset, splitterPos - offset));
offset = splitterPos + splitter.size();
}
else
{
lines.push_back(input.substr(offset));
break;
}
}
lines.swap(output);
}
}
// gtest:
class SplitStringTest: public testing::Test
{
};
TEST_F(SplitStringTest, EmptyStringAndSplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(Core::String(), Core::String(), result));
}
TEST_F(SplitStringTest, NonEmptyStringAndEmptySplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(L"xy", Core::String(), result));
}
TEST_F(SplitStringTest, EmptyStringAndNonEmptySplitter)
{
std::list<Core::String> result;
Core::SplitString(Core::String(), Core::String(L","), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(Core::String(), *result.begin());
}
TEST_F(SplitStringTest, OneCharSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,y", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
Core::SplitString(L",xy", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L"xy", *result.rbegin());
Core::SplitString(L"xy,", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"xy", *result.begin());
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, TwoCharsSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,.y,z", L",.", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
Core::SplitString(L"x,,y,z", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
}
TEST_F(SplitStringTest, RecursiveSplitter)
{
std::list<Core::String> result;
Core::SplitString(L",,,", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L",", *result.rbegin());
Core::SplitString(L",.,.,", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L".,", *result.rbegin());
Core::SplitString(L"x,.,.,y", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L".,y", *result.rbegin());
Core::SplitString(L",.,,.,", L",.,", result);
ASSERT_EQ(3, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(Core::String(), *(++result.begin()));
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, NullTerminators)
{
std::list<Core::String> result;
Core::SplitString(L"xy", Core::String(L"\0", 1), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(L"xy", *result.begin());
Core::SplitString(Core::String(L"x\0y", 3), Core::String(L"\0", 1), result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
}
The STL does not have such a method available already.
However, you can either use C's strtok() function by using the std::string::c_str() member, or you can write your own. Here is a code sample I found after a quick Google search ("STL string split"):
void Tokenize(const string& str,
vector<string>& tokens,
const string& delimiters = " ")
{
// Skip delimiters at beginning.
string::size_type lastPos = str.find_first_not_of(delimiters, 0);
// Find first "non-delimiter".
string::size_type pos = str.find_first_of(delimiters, lastPos);
while (string::npos != pos || string::npos != lastPos)
{
// Found a token, add it to the vector.
tokens.push_back(str.substr(lastPos, pos - lastPos));
// Skip delimiters. Note the "not_of"
lastPos = str.find_first_not_of(delimiters, pos);
// Find next "non-delimiter"
pos = str.find_first_of(delimiters, lastPos);
}
}
Taken from: http://oopweb.com/CPP/Documents/CPPHOWTO/Volume/C++Programming-HOWTO-7.html
If you have questions about the code sample, leave a comment and I will explain.
And just because it does not implement a typedef called iterator or overload the << operator does not mean it is bad code. I use C functions quite frequently. For example, printf and scanf both are faster than std::cin and std::cout (significantly), the fopen syntax is a lot more friendly for binary types, and they also tend to produce smaller EXEs.
Don't get sold on this "Elegance over performance" deal.
There is a function named strtok.
#include<string>
using namespace std;
vector<string> split(char* str,const char* delim)
{
char* saveptr;
char* token = strtok_r(str,delim,&saveptr);
vector<string> result;
while(token != NULL)
{
result.push_back(token);
token = strtok_r(NULL,delim,&saveptr);
}
return result;
}
I use the following code:
namespace Core
{
typedef std::wstring String;
void SplitString(const Core::String& input, const Core::String& splitter, std::list<Core::String>& output)
{
if (splitter.empty())
{
throw std::invalid_argument(); // for example
}
std::list<Core::String> lines;
Core::String::size_type offset = 0;
for (;;)
{
Core::String::size_type splitterPos = input.find(splitter, offset);
if (splitterPos != Core::String::npos)
{
lines.push_back(input.substr(offset, splitterPos - offset));
offset = splitterPos + splitter.size();
}
else
{
lines.push_back(input.substr(offset));
break;
}
}
lines.swap(output);
}
}
// gtest:
class SplitStringTest: public testing::Test
{
};
TEST_F(SplitStringTest, EmptyStringAndSplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(Core::String(), Core::String(), result));
}
TEST_F(SplitStringTest, NonEmptyStringAndEmptySplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(L"xy", Core::String(), result));
}
TEST_F(SplitStringTest, EmptyStringAndNonEmptySplitter)
{
std::list<Core::String> result;
Core::SplitString(Core::String(), Core::String(L","), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(Core::String(), *result.begin());
}
TEST_F(SplitStringTest, OneCharSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,y", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
Core::SplitString(L",xy", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L"xy", *result.rbegin());
Core::SplitString(L"xy,", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"xy", *result.begin());
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, TwoCharsSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,.y,z", L",.", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
Core::SplitString(L"x,,y,z", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
}
TEST_F(SplitStringTest, RecursiveSplitter)
{
std::list<Core::String> result;
Core::SplitString(L",,,", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L",", *result.rbegin());
Core::SplitString(L",.,.,", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L".,", *result.rbegin());
Core::SplitString(L"x,.,.,y", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L".,y", *result.rbegin());
Core::SplitString(L",.,,.,", L",.,", result);
ASSERT_EQ(3, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(Core::String(), *(++result.begin()));
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, NullTerminators)
{
std::list<Core::String> result;
Core::SplitString(L"xy", Core::String(L"\0", 1), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(L"xy", *result.begin());
Core::SplitString(Core::String(L"x\0y", 3), Core::String(L"\0", 1), result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
}
LazyStringSplitter:
#include <string>
#include <algorithm>
#include <unordered_set>
using namespace std;
class LazyStringSplitter
{
string::const_iterator start, finish;
unordered_set<char> chop;
public:
// Empty Constructor
explicit LazyStringSplitter()
{}
explicit LazyStringSplitter (const string cstr, const string delims)
: start(cstr.begin())
, finish(cstr.end())
, chop(delims.begin(), delims.end())
{}
void operator () (const string cstr, const string delims)
{
chop.insert(delims.begin(), delims.end());
start = cstr.begin();
finish = cstr.end();
}
bool empty() const { return (start >= finish); }
string next()
{
// return empty string
// if ran out of characters
if (empty())
return string("");
auto runner = find_if(start, finish, [&](char c) {
return chop.count(c) == 1;
});
// construct next string
string ret(start, runner);
start = runner + 1;
// Never return empty string
// + tail recursion makes this method efficient
return !ret.empty() ? ret : next();
}
};
LazyStringSplitter because of one reason - It does not split the string in one go.next which returns the next string that is split from the originalTEST PROGRAM
#include <iostream>
using namespace std;
int main()
{
LazyStringSplitter splitter;
// split at the characters ' ', '!', '.', ','
splitter("This, is a string. And here is another string! Let's test and see how well this does.", " !.,");
while (!splitter.empty())
cout << splitter.next() << endl;
return 0;
}
OUTPUT
This
is
a
string
And
here
is
another
string
Let's
test
and
see
how
well
this
does
Next plan to improve this is to implement begin and end methods so that one can do something like:
vector<string> split_string(splitter.begin(), splitter.end());
What about this:
#include <string>
#include <vector>
using namespace std;
vector<string> split(string str, const char delim) {
vector<string> v;
string tmp;
for(string::const_iterator i; i = str.begin(); i <= str.end(); ++i) {
if(*i != delim && i != str.end()) {
tmp += *i;
} else {
v.push_back(tmp);
tmp = "";
}
}
return v;
}
Here's a simple solution that uses only the standard regex library
#include <regex>
#include <string>
#include <vector>
std::vector<string> Tokenize( const string str, const std::regex regex )
{
using namespace std;
std::vector<string> result;
sregex_token_iterator it( str.begin(), str.end(), regex, -1 );
sregex_token_iterator reg_end;
for ( ; it != reg_end; ++it ) {
if ( !it->str().empty() ) //token could be empty:check
result.emplace_back( it->str() );
}
return result;
}
The regex argument allows checking for multiple arguments (spaces, commas, etc.)
I usually only check to split on spaces and commas, so I also have this default function:
std::vector<string> TokenizeDefault( const string str )
{
using namespace std;
regex re( "[\\s,]+" );
return Tokenize( str, re );
}
The "[\\s,]+" checks for spaces (\\s) and commas (,).
Note, if you want to split wstring instead of string,
std::regex to std::wregexsregex_token_iterator to wsregex_token_iteratorNote, you might also want to take the string argument by reference, depending on your compiler.
Here's my entry:
template <typename Container, typename InputIter, typename ForwardIter>
Container
split(InputIter first, InputIter last,
ForwardIter s_first, ForwardIter s_last)
{
Container output;
while (true) {
auto pos = std::find_first_of(first, last, s_first, s_last);
output.emplace_back(first, pos);
if (pos == last) {
break;
}
first = ++pos;
}
return output;
}
template <typename Output = std::vector<std::string>,
typename Input = std::string,
typename Delims = std::string>
Output
split(const Input& input, const Delims& delims = " ")
{
using std::cbegin;
using std::cend;
return split<Output>(cbegin(input), cend(input),
cbegin(delims), cend(delims));
}
auto vec = split("Mary had a little lamb");
The first definition is an STL-style generic function taking two pair of iterators. The second is a convenience function to save you having to do all the begin()s and end()s yourself. You can also specify the output container type as a template parameter if you wanted to use a list, for example.
What makes it elegant (IMO) is that unlike most of the other answers, it's not restricted to strings but will work with any STL-compatible container. Without any change to the code above, you can say:
using vec_of_vecs_t = std::vector<std::vector<int>>;
std::vector<int> v{1, 2, 0, 3, 4, 5, 0, 7, 8, 0, 9};
auto r = split<vec_of_vecs_t>(v, std::initializer_list<int>{0, 2});
which will split the vector v into separate vectors every time a 0 or a 2 is encountered.
(There's also the added bonus that with strings, this implementation is faster than both strtok()- and getline()-based versions, at least on my system.)
A possible solution using Boost might be:
#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));
This approach might be even faster than the stringstream approach. And since this is a generic template function it can be used to split other types of strings (wchar, etc. or UTF-8) using all kinds of delimiters.
See the documentation for details.
Here's another solution. It's compact and reasonably efficient:
std::vector<std::string> split(const std::string &text, char sep) {
std::vector<std::string> tokens;
std::size_t start = 0, end = 0;
while ((end = text.find(sep, start)) != std::string::npos) {
tokens.push_back(text.substr(start, end - start));
start = end + 1;
}
tokens.push_back(text.substr(start));
return tokens;
}
It can easily be templatised to handle string separators, wide strings, etc.
Note that splitting "" results in a single empty string and splitting "," (ie. sep) results in two empty strings.
It can also be easily expanded to skip empty tokens:
std::vector<std::string> split(const std::string &text, char sep) {
std::vector<std::string> tokens;
std::size_t start = 0, end = 0;
while ((end = text.find(sep, start)) != std::string::npos) {
if (end != start) {
tokens.push_back(text.substr(start, end - start));
}
start = end + 1;
}
if (end != start) {
tokens.push_back(text.substr(start));
}
return tokens;
}
If splitting a string at multiple delimiters while skipping empty tokens is desired, this version may be used:
std::vector<std::string> split(const std::string& text, const std::string& delims)
{
std::vector<std::string> tokens;
std::size_t start = text.find_first_not_of(delims), end = 0;
while((end = text.find_first_of(delims, start)) != std::string::npos)
{
tokens.push_back(text.substr(start, end - start));
start = text.find_first_not_of(delims, end);
}
if(start != std::string::npos)
tokens.push_back(text.substr(start));
return tokens;
}
As a hobbyist, this is the first solution that came to my mind. I'm kind of curious why I haven't seen a similar solution here yet, is there something fundamentally wrong with how I did it?
#include <iostream>
#include <string>
#include <vector>
std::vector<std::string> split(const std::string &s, const std::string &delims)
{
std::vector<std::string> result;
std::string::size_type pos = 0;
while (std::string::npos != (pos = s.find_first_not_of(delims, pos))) {
auto pos2 = s.find_first_of(delims, pos);
result.emplace_back(s.substr(pos, std::string::npos == pos2 ? pos2 : pos2 - pos));
pos = pos2;
}
return result;
}
int main()
{
std::string text{"And then I said: \"I don't get it, why would you even do that!?\""};
std::string delims{" :;\".,?!"};
auto words = split(text, delims);
std::cout << "\nSentence:\n " << text << "\n\nWords:";
for (const auto &w : words) {
std::cout << "\n " << w;
}
return 0;
}
I made this because I needed an easy way to split strings and c-based strings... Hopefully someone else can find it useful as well. Also it doesn't rely on tokens and you can use fields as delimiters, which is another key I needed.
I'm sure there's improvements that can be made to even further improve its elegance and please do by all means
StringSplitter.hpp:
#include <vector>
#include <iostream>
#include <string.h>
using namespace std;
class StringSplit
{
private:
void copy_fragment(char*, char*, char*);
void copy_fragment(char*, char*, char);
bool match_fragment(char*, char*, int);
int untilnextdelim(char*, char);
int untilnextdelim(char*, char*);
void assimilate(char*, char);
void assimilate(char*, char*);
bool string_contains(char*, char*);
long calc_string_size(char*);
void copy_string(char*, char*);
public:
vector<char*> split_cstr(char);
vector<char*> split_cstr(char*);
vector<string> split_string(char);
vector<string> split_string(char*);
char* String;
bool do_string;
bool keep_empty;
vector<char*> Container;
vector<string> ContainerS;
StringSplit(char * in)
{
String = in;
}
StringSplit(string in)
{
size_t len = calc_string_size((char*)in.c_str());
String = new char[len + 1];
memset(String, 0, len + 1);
copy_string(String, (char*)in.c_str());
do_string = true;
}
~StringSplit()
{
for (int i = 0; i < Container.size(); i++)
{
if (Container[i] != NULL)
{
delete[] Container[i];
}
}
if (do_string)
{
delete[] String;
}
}
};
StringSplitter.cpp:
#include <string.h>
#include <iostream>
#include <vector>
#include "StringSplit.hpp"
using namespace std;
void StringSplit::assimilate(char*src, char delim)
{
int until = untilnextdelim(src, delim);
if (until > 0)
{
char * temp = new char[until + 1];
memset(temp, 0, until + 1);
copy_fragment(temp, src, delim);
if (keep_empty || *temp != 0)
{
if (!do_string)
{
Container.push_back(temp);
}
else
{
string x = temp;
ContainerS.push_back(x);
}
}
else
{
delete[] temp;
}
}
}
void StringSplit::assimilate(char*src, char* delim)
{
int until = untilnextdelim(src, delim);
if (until > 0)
{
char * temp = new char[until + 1];
memset(temp, 0, until + 1);
copy_fragment(temp, src, delim);
if (keep_empty || *temp != 0)
{
if (!do_string)
{
Container.push_back(temp);
}
else
{
string x = temp;
ContainerS.push_back(x);
}
}
else
{
delete[] temp;
}
}
}
long StringSplit::calc_string_size(char* _in)
{
long i = 0;
while (*_in++)
{
i++;
}
return i;
}
bool StringSplit::string_contains(char* haystack, char* needle)
{
size_t len = calc_string_size(needle);
size_t lenh = calc_string_size(haystack);
while (lenh--)
{
if (match_fragment(haystack + lenh, needle, len))
{
return true;
}
}
return false;
}
bool StringSplit::match_fragment(char* _src, char* cmp, int len)
{
while (len--)
{
if (*(_src + len) != *(cmp + len))
{
return false;
}
}
return true;
}
int StringSplit::untilnextdelim(char* _in, char delim)
{
size_t len = calc_string_size(_in);
if (*_in == delim)
{
_in += 1;
return len - 1;
}
int c = 0;
while (*(_in + c) != delim && c < len)
{
c++;
}
return c;
}
int StringSplit::untilnextdelim(char* _in, char* delim)
{
int s = calc_string_size(delim);
int c = 1 + s;
if (!string_contains(_in, delim))
{
return calc_string_size(_in);
}
else if (match_fragment(_in, delim, s))
{
_in += s;
return calc_string_size(_in);
}
while (!match_fragment(_in + c, delim, s))
{
c++;
}
return c;
}
void StringSplit::copy_fragment(char* dest, char* src, char delim)
{
if (*src == delim)
{
src++;
}
int c = 0;
while (*(src + c) != delim && *(src + c))
{
*(dest + c) = *(src + c);
c++;
}
*(dest + c) = 0;
}
void StringSplit::copy_string(char* dest, char* src)
{
int i = 0;
while (*(src + i))
{
*(dest + i) = *(src + i);
i++;
}
}
void StringSplit::copy_fragment(char* dest, char* src, char* delim)
{
size_t len = calc_string_size(delim);
size_t lens = calc_string_size(src);
if (match_fragment(src, delim, len))
{
src += len;
lens -= len;
}
int c = 0;
while (!match_fragment(src + c, delim, len) && (c < lens))
{
*(dest + c) = *(src + c);
c++;
}
*(dest + c) = 0;
}
vector<char*> StringSplit::split_cstr(char Delimiter)
{
int i = 0;
while (*String)
{
if (*String != Delimiter && i == 0)
{
assimilate(String, Delimiter);
}
if (*String == Delimiter)
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return Container;
}
vector<string> StringSplit::split_string(char Delimiter)
{
do_string = true;
int i = 0;
while (*String)
{
if (*String != Delimiter && i == 0)
{
assimilate(String, Delimiter);
}
if (*String == Delimiter)
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return ContainerS;
}
vector<char*> StringSplit::split_cstr(char* Delimiter)
{
int i = 0;
size_t LenDelim = calc_string_size(Delimiter);
while(*String)
{
if (!match_fragment(String, Delimiter, LenDelim) && i == 0)
{
assimilate(String, Delimiter);
}
if (match_fragment(String, Delimiter, LenDelim))
{
assimilate(String,Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return Container;
}
vector<string> StringSplit::split_string(char* Delimiter)
{
do_string = true;
int i = 0;
size_t LenDelim = calc_string_size(Delimiter);
while (*String)
{
if (!match_fragment(String, Delimiter, LenDelim) && i == 0)
{
assimilate(String, Delimiter);
}
if (match_fragment(String, Delimiter, LenDelim))
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return ContainerS;
}
Examples:
int main(int argc, char*argv[])
{
StringSplit ss = "This:CUT:is:CUT:an:CUT:example:CUT:cstring";
vector<char*> Split = ss.split_cstr(":CUT:");
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
Will output:
This
is
an
example
cstring
int main(int argc, char*argv[])
{
StringSplit ss = "This:is:an:example:cstring";
vector<char*> Split = ss.split_cstr(':');
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
int main(int argc, char*argv[])
{
string mystring = "This[SPLIT]is[SPLIT]an[SPLIT]example[SPLIT]string";
StringSplit ss = mystring;
vector<string> Split = ss.split_string("[SPLIT]");
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
int main(int argc, char*argv[])
{
string mystring = "This|is|an|example|string";
StringSplit ss = mystring;
vector<string> Split = ss.split_string('|');
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
To keep empty entries (by default empties will be excluded):
StringSplit ss = mystring;
ss.keep_empty = true;
vector<string> Split = ss.split_string(":DELIM:");
The goal was to make it similar to C#'s Split() method where splitting a string is as easy as:
String[] Split =
"Hey:cut:what's:cut:your:cut:name?".Split(new[]{":cut:"}, StringSplitOptions.None);
foreach(String X in Split)
{
Console.Write(X);
}
I hope someone else can find this as useful as I do.
My implementation can be an alternative solution:
std::vector<std::wstring> SplitString(const std::wstring & String, const std::wstring & Seperator)
{
std::vector<std::wstring> Lines;
size_t stSearchPos = 0;
size_t stFoundPos;
while (stSearchPos < String.size() - 1)
{
stFoundPos = String.find(Seperator, stSearchPos);
stFoundPos = (stFoundPos == std::string::npos) ? String.size() : stFoundPos;
Lines.push_back(String.substr(stSearchPos, stFoundPos - stSearchPos));
stSearchPos = stFoundPos + Seperator.size();
}
return Lines;
}
Test code:
std::wstring MyString(L"Part 1SEPsecond partSEPlast partSEPend");
std::vector<std::wstring> Parts = IniFile::SplitString(MyString, L"SEP");
std::wcout << L"The string: " << MyString << std::endl;
for (std::vector<std::wstring>::const_iterator it=Parts.begin(); it<Parts.end(); ++it)
{
std::wcout << *it << L"<---" << std::endl;
}
std::wcout << std::endl;
MyString = L"this,time,a,comma separated,string";
std::wcout << L"The string: " << MyString << std::endl;
Parts = IniFile::SplitString(MyString, L",");
for (std::vector<std::wstring>::const_iterator it=Parts.begin(); it<Parts.end(); ++it)
{
std::wcout << *it << L"<---" << std::endl;
}
Output of the test code:
The string: Part 1SEPsecond partSEPlast partSEPend
Part 1<---
second part<---
last part<---
end<---
The string: this,time,a,comma separated,string
this<---
time<---
a<---
comma separated<---
string<---
This is a function I wrote that helps me do a lot. It helped me when doing protocol for WebSockets.
using namespace std;
#include <iostream>
#include <vector>
#include <sstream>
#include <string>
vector<string> split ( string input , string split_id ) {
vector<string> result;
int i = 0;
bool add;
string temp;
stringstream ss;
size_t found;
string real;
int r = 0;
while ( i != input.length() ) {
add = false;
ss << input.at(i);
temp = ss.str();
found = temp.find(split_id);
if ( found != string::npos ) {
add = true;
real.append ( temp , 0 , found );
} else if ( r > 0 && ( i+1 ) == input.length() ) {
add = true;
real.append ( temp , 0 , found );
}
if ( add ) {
result.push_back(real);
ss.str(string());
ss.clear();
temp.clear();
real.clear();
r = 0;
}
i++;
r++;
}
return result;
}
int main() {
string s = "S,o,m,e,w,h,e,r,e, down the road \n In a really big C++ house. \n Lives a little old lady. \n That no one ever knew. \n She comes outside. \n In the very hot sun. \n\n\n\n\n\n\n\n And throws C++ at us. \n The End. FIN.";
vector < string > Token;
Token = split ( s , "," );
for ( int i = 0 ; i < Token.size(); i++) cout << Token.at(i) << endl;
cout << endl << Token.size();
int a;
cin >> a;
return a;
}
So far I used the one in Boost, but I needed something that doesn't depends on it, so I came to this:
static void Split(std::vector<std::string>& lst, const std::string& input, const std::string& separators, bool remove_empty = true)
{
std::ostringstream word;
for (size_t n = 0; n < input.size(); ++n)
{
if (std::string::npos == separators.find(input[n]))
word << input[n];
else
{
if (!word.str().empty() || !remove_empty)
lst.push_back(word.str());
word.str("");
}
}
if (!word.str().empty() || !remove_empty)
lst.push_back(word.str());
}
A good point is that in separators you can pass more than one character.
C++17 version without any memory allocation (except may be for std::function)
void iter_words(const std::string_view& input, const std::function<void(std::string_view)>& process_word) {
auto itr = input.begin();
auto consume_whitespace = [&]() {
for(; itr != input.end(); ++itr) {
if(!isspace(*itr))
return;
}
};
auto consume_letters = [&]() {
for(; itr != input.end(); ++itr) {
if(isspace(*itr))
return;
}
};
while(true) {
consume_whitespace();
if(itr == input.end())
return;
auto word_start = itr - input.begin();
consume_letters();
auto word_end = itr - input.begin();
process_word(input.substr(word_start, word_end - word_start));
}
}
int main() {
iter_words("foo bar", [](std::string_view sv) {
std::cout << "Got word: " << sv << '\n';
});
return 0;
}
Here is my version
#include <vector>
inline std::vector<std::string> Split(const std::string &str, const std::string &delim = " ")
{
std::vector<std::string> tokens;
if (str.size() > 0)
{
if (delim.size() > 0)
{
std::string::size_type currPos = 0, prevPos = 0;
while ((currPos = str.find(delim, prevPos)) != std::string::npos)
{
std::string item = str.substr(prevPos, currPos - prevPos);
if (item.size() > 0)
{
tokens.push_back(item);
}
prevPos = currPos + 1;
}
tokens.push_back(str.substr(prevPos));
}
else
{
tokens.push_back(str);
}
}
return tokens;
}
It works with multi-character delimiters. It prevents empty tokens to get in your results. It uses a single header. It returns the string as one single token when you provide no delimiter. It also returns an empty result if the string is empty. It is unfortunately inefficient because of the huge std::vector copy UNLESS you are compiling using C++11, which should be using the move schematic. In C++11, this code should be fast.
Heres a regex solution that only uses the standard regex library. (I'm a little rusty, so there may be a few syntax errors, but this is at least the general idea)
#include <regex.h>
#include <string.h>
#include <vector.h>
using namespace std;
vector<string> split(string s){
regex r ("\\w+"); //regex matches whole words, (greedy, so no fragment words)
regex_iterator<string::iterator> rit ( s.begin(), s.end(), r );
regex_iterator<string::iterator> rend; //iterators to iterate thru words
vector<string> result<regex_iterator>(rit, rend);
return result; //iterates through the matches to fill the vector
}
I use this to split string by a delimiter. The first puts the results in a pre-constructed vector, the second returns a new vector.
#include <string>
#include <sstream>
#include <vector>
#include <iterator>
template <typename Out>
void split(const std::string &s, char delim, Out result) {
std::istringstream iss(s);
std::string item;
while (std::getline(iss, item, delim)) {
*result++ = item;
}
}
std::vector<std::string> split(const std::string &s, char delim) {
std::vector<std::string> elems;
split(s, delim, std::back_inserter(elems));
return elems;
}
Note that this solution does not skip empty tokens, so the following will find 4 items, one of which is empty:
std::vector<std::string> x = split("one:two::three", ':');
#include <vector>
#include <string>
#include <sstream>
int main()
{
std::string str("Split me by whitespaces");
std::string buf; // Have a buffer string
std::stringstream ss(str); // Insert the string into a stream
std::vector<std::string> tokens; // Create vector to hold our words
while (ss >> buf)
tokens.push_back(buf);
return 0;
}
#include <iostream>
#include <regex>
using namespace std;
int main() {
string s = "foo bar baz";
regex e("\\s+");
regex_token_iterator<string::iterator> i(s.begin(), s.end(), e, -1);
regex_token_iterator<string::iterator> end;
while (i != end)
cout << " [" << *i++ << "]";
}
IMO, this is the closest thing to python's re.split(). See cplusplus.com for more information about regex_token_iterator. The -1 (4th argument in regex_token_iterator ctor) is the section of the sequence that is not matched, using the match as separator.
I believe no one has posted this solution yet. Instead of using delimiters directly, it basically does the same as boost::split(), i.e., it allows you to pass a predicate that returns true if a char is a delimiter, and false otherwise. I think this gives the programmer a lot more control, and the great thing is you don't need boost.
template <class Container, class String, class Predicate>
void split(Container& output, const String& input,
const Predicate& pred, bool trimEmpty = false) {
auto it = begin(input);
auto itLast = it;
while (it = find_if(it, end(input), pred), it != end(input)) {
if (not (trimEmpty and it == itLast)) {
output.emplace_back(itLast, it);
}
++it;
itLast = it;
}
}
Then you can use it like this:
struct Delim {
bool operator()(char c) {
return not isalpha(c);
}
};
int main() {
string s("#include<iostream>\n"
"int main() { std::cout << \"Hello world!\" << std::endl; }");
vector<string> v;
split(v, s, Delim(), true);
/* Which is also the same as */
split(v, s, [](char c) { return not isalpha(c); }, true);
for (const auto& i : v) {
cout << i << endl;
}
}
Using std::stringstream as you have works perfectly fine, and do exactly what you wanted. If you're just looking for different way of doing things though, you can use std::find()/std::find_first_of() and std::string::substr().
Here's an example:
#include <iostream>
#include <string>
int main()
{
std::string s("Somewhere down the road");
std::string::size_type prev_pos = 0, pos = 0;
while( (pos = s.find(' ', pos)) != std::string::npos )
{
std::string substring( s.substr(prev_pos, pos-prev_pos) );
std::cout << substring << '\n';
prev_pos = ++pos;
}
std::string substring( s.substr(prev_pos, pos-prev_pos) ); // Last word
std::cout << substring << '\n';
return 0;
}
#include<iostream>
#include<string>
#include<sstream>
#include<vector>
using namespace std;
vector<string> split(const string &s, char delim) {
vector<string> elems;
stringstream ss(s);
string item;
while (getline(ss, item, delim)) {
elems.push_back(item);
}
return elems;
}
int main() {
vector<string> x = split("thi is an sample test",' ');
unsigned int i;
for(i=0;i<x.size();i++)
cout<<i<<":"<<x[i]<<endl;
return 0;
}
Yet another flexible and fast way
template<typename Operator>
void tokenize(Operator& op, const char* input, const char* delimiters) {
const char* s = input;
const char* e = s;
while (*e != 0) {
e = s;
while (*e != 0 && strchr(delimiters, *e) == 0) ++e;
if (e - s > 0) {
op(s, e - s);
}
s = e + 1;
}
}
To use it with a vector of strings (Edit: Since someone pointed out not to inherit STL classes... hrmf ;) ) :
template<class ContainerType>
class Appender {
public:
Appender(ContainerType& container) : container_(container) {;}
void operator() (const char* s, unsigned length) {
container_.push_back(std::string(s,length));
}
private:
ContainerType& container_;
};
std::vector<std::string> strVector;
Appender v(strVector);
tokenize(v, "A number of words to be tokenized", " \t");
That's it! And that's just one way to use the tokenizer, like how to just count words:
class WordCounter {
public:
WordCounter() : noOfWords(0) {}
void operator() (const char*, unsigned) {
++noOfWords;
}
unsigned noOfWords;
};
WordCounter wc;
tokenize(wc, "A number of words to be counted", " \t");
ASSERT( wc.noOfWords == 7 );
Limited by imagination ;)
LazyStringSplitter:
#include <string>
#include <algorithm>
#include <unordered_set>
using namespace std;
class LazyStringSplitter
{
string::const_iterator start, finish;
unordered_set<char> chop;
public:
// Empty Constructor
explicit LazyStringSplitter()
{}
explicit LazyStringSplitter (const string cstr, const string delims)
: start(cstr.begin())
, finish(cstr.end())
, chop(delims.begin(), delims.end())
{}
void operator () (const string cstr, const string delims)
{
chop.insert(delims.begin(), delims.end());
start = cstr.begin();
finish = cstr.end();
}
bool empty() const { return (start >= finish); }
string next()
{
// return empty string
// if ran out of characters
if (empty())
return string("");
auto runner = find_if(start, finish, [&](char c) {
return chop.count(c) == 1;
});
// construct next string
string ret(start, runner);
start = runner + 1;
// Never return empty string
// + tail recursion makes this method efficient
return !ret.empty() ? ret : next();
}
};
LazyStringSplitter because of one reason - It does not split the string in one go.next which returns the next string that is split from the originalTEST PROGRAM
#include <iostream>
using namespace std;
int main()
{
LazyStringSplitter splitter;
// split at the characters ' ', '!', '.', ','
splitter("This, is a string. And here is another string! Let's test and see how well this does.", " !.,");
while (!splitter.empty())
cout << splitter.next() << endl;
return 0;
}
OUTPUT
This
is
a
string
And
here
is
another
string
Let's
test
and
see
how
well
this
does
Next plan to improve this is to implement begin and end methods so that one can do something like:
vector<string> split_string(splitter.begin(), splitter.end());
I have just written a fine example of how to split a char by symbol, which then places each array of chars (words seperated by your symbol) into a vector. For simplicity i made the vector type of std string.
I hope this helps and is readable to you.
#include <vector>
#include <string>
#include <iostream>
void push(std::vector<std::string> &WORDS, std::string &TMP){
WORDS.push_back(TMP);
TMP = "";
}
std::vector<std::string> mySplit(char STRING[]){
std::vector<std::string> words;
std::string s;
for(unsigned short i = 0; i < strlen(STRING); i++){
if(STRING[i] != ' '){
s += STRING[i];
}else{
push(words, s);
}
}
push(words, s);//Used to get last split
return words;
}
int main(){
char string[] = "My awesome string.";
std::cout << mySplit(string)[2];
std::cin.get();
return 0;
}
#include <iostream>
#include <vector>
using namespace std;
int main() {
string str = "ABC AABCD CDDD RABC GHTTYU FR";
str += " "; //dirty hack: adding extra space to the end
vector<string> v;
for (int i=0; i<(int)str.size(); i++) {
int a, b;
a = i;
for (int j=i; j<(int)str.size(); j++) {
if (str[j] == ' ') {
b = j;
i = j;
break;
}
}
v.push_back(str.substr(a, b-a));
}
for (int i=0; i<v.size(); i++) {
cout<<v[i].size()<<" "<<v[i]<<endl;
}
return 0;
}
Here is my solution using C++11 and the STL. It should be reasonably efficient:
#include <vector>
#include <string>
#include <cstring>
#include <iostream>
#include <algorithm>
#include <functional>
std::vector<std::string> split(const std::string& s)
{
std::vector<std::string> v;
const auto end = s.end();
auto to = s.begin();
decltype(to) from;
while((from = std::find_if(to, end,
[](char c){ return !std::isspace(c); })) != end)
{
to = std::find_if(from, end, [](char c){ return std::isspace(c); });
v.emplace_back(from, to);
}
return v;
}
int main()
{
std::string s = "this is the string to split";
auto v = split(s);
for(auto&& s: v)
std::cout << s << '\n';
}
Output:
this
is
the
string
to
split
Short and elegant
#include <vector>
#include <string>
using namespace std;
vector<string> split(string data, string token)
{
vector<string> output;
size_t pos = string::npos; // size_t to avoid improbable overflow
do
{
pos = data.find(token);
output.push_back(data.substr(0, pos));
if (string::npos != pos)
data = data.substr(pos + token.size());
} while (string::npos != pos);
return output;
}
can use any string as delimiter, also can be used with binary data (std::string supports binary data, including nulls)
using:
auto a = split("this!!is!!!example!string", "!!");
output:
this
is
!example!string
I like to use the boost/regex methods for this task since they provide maximum flexibility for specifying the splitting criteria.
#include <iostream>
#include <string>
#include <boost/regex.hpp>
int main() {
std::string line("A:::line::to:split");
const boost::regex re(":+"); // one or more colons
// -1 means find inverse matches aka split
boost::sregex_token_iterator tokens(line.begin(),line.end(),re,-1);
boost::sregex_token_iterator end;
for (; tokens != end; ++tokens)
std::cout << *tokens << std::endl;
}
#include <iostream>
#include <string>
#include <sstream>
#include <algorithm>
#include <iterator>
#include <vector>
int main() {
using namespace std;
int n=8;
string sentence = "10 20 30 40 5 6 7 8";
istringstream iss(sentence);
vector<string> tokens;
copy(istream_iterator<string>(iss),
istream_iterator<string>(),
back_inserter(tokens));
for(int i=0;i<n;i++){
cout<<tokens.at(i);
}
}
void splitString(string str, char delim, string array[], const int arraySize)
{
int delimPosition, subStrSize, subStrStart = 0;
for (int index = 0; delimPosition != -1; index++)
{
delimPosition = str.find(delim, subStrStart);
subStrSize = delimPosition - subStrStart;
array[index] = str.substr(subStrStart, subStrSize);
subStrStart =+ (delimPosition + 1);
}
}
This is similar to Stack Overflow question How do I tokenize a string in C++?.
#include <iostream>
#include <string>
#include <boost/tokenizer.hpp>
using namespace std;
using namespace boost;
int main(int argc, char** argv)
{
string text = "token test\tstring";
char_separator<char> sep(" \t");
tokenizer<char_separator<char>> tokens(text, sep);
for (const string& t : tokens)
{
cout << t << "." << endl;
}
}
I like the following because it puts the results into a vector, supports a string as a delim and gives control over keeping empty values. But, it doesn't look as good then.
#include <ostream>
#include <string>
#include <vector>
#include <algorithm>
#include <iterator>
using namespace std;
vector<string> split(const string& s, const string& delim, const bool keep_empty = true) {
vector<string> result;
if (delim.empty()) {
result.push_back(s);
return result;
}
string::const_iterator substart = s.begin(), subend;
while (true) {
subend = search(substart, s.end(), delim.begin(), delim.end());
string temp(substart, subend);
if (keep_empty || !temp.empty()) {
result.push_back(temp);
}
if (subend == s.end()) {
break;
}
substart = subend + delim.size();
}
return result;
}
int main() {
const vector<string> words = split("So close no matter how far", " ");
copy(words.begin(), words.end(), ostream_iterator<string>(cout, "\n"));
}
Of course, Boost has a split() that works partially like that. And, if by 'white-space', you really do mean any type of white-space, using Boost's split with is_any_of() works great.
For those with whom it does not sit well to sacrifice all efficiency for code size and see "efficient" as a type of elegance, the following should hit a sweet spot (and I think the template container class is an awesomely elegant addition.):
template < class ContainerT >
void tokenize(const std::string& str, ContainerT& tokens,
const std::string& delimiters = " ", bool trimEmpty = false)
{
std::string::size_type pos, lastPos = 0, length = str.length();
using value_type = typename ContainerT::value_type;
using size_type = typename ContainerT::size_type;
while(lastPos < length + 1)
{
pos = str.find_first_of(delimiters, lastPos);
if(pos == std::string::npos)
{
pos = length;
}
if(pos != lastPos || !trimEmpty)
tokens.push_back(value_type(str.data()+lastPos,
(size_type)pos-lastPos ));
lastPos = pos + 1;
}
}
I usually choose to use std::vector<std::string> types as my second parameter (ContainerT)... but list<> is way faster than vector<> for when direct access is not needed, and you can even create your own string class and use something like std::list<subString> where subString does not do any copies for incredible speed increases.
It's more than double as fast as the fastest tokenize on this page and almost 5 times faster than some others. Also with the perfect parameter types you can eliminate all string and list copies for additional speed increases.
Additionally it does not do the (extremely inefficient) return of result, but rather it passes the tokens as a reference, thus also allowing you to build up tokens using multiple calls if you so wished.
Lastly it allows you to specify whether to trim empty tokens from the results via a last optional parameter.
All it needs is std::string... the rest are optional. It does not use streams or the boost library, but is flexible enough to be able to accept some of these foreign types naturally.
Yet another flexible and fast way
template<typename Operator>
void tokenize(Operator& op, const char* input, const char* delimiters) {
const char* s = input;
const char* e = s;
while (*e != 0) {
e = s;
while (*e != 0 && strchr(delimiters, *e) == 0) ++e;
if (e - s > 0) {
op(s, e - s);
}
s = e + 1;
}
}
To use it with a vector of strings (Edit: Since someone pointed out not to inherit STL classes... hrmf ;) ) :
template<class ContainerType>
class Appender {
public:
Appender(ContainerType& container) : container_(container) {;}
void operator() (const char* s, unsigned length) {
container_.push_back(std::string(s,length));
}
private:
ContainerType& container_;
};
std::vector<std::string> strVector;
Appender v(strVector);
tokenize(v, "A number of words to be tokenized", " \t");
That's it! And that's just one way to use the tokenizer, like how to just count words:
class WordCounter {
public:
WordCounter() : noOfWords(0) {}
void operator() (const char*, unsigned) {
++noOfWords;
}
unsigned noOfWords;
};
WordCounter wc;
tokenize(wc, "A number of words to be counted", " \t");
ASSERT( wc.noOfWords == 7 );
Limited by imagination ;)
#include <iostream>
#include <string>
#include <deque>
std::deque<std::string> split(
const std::string& line,
std::string::value_type delimiter,
bool skipEmpty = false
) {
std::deque<std::string> parts{};
if (!skipEmpty && !line.empty() && delimiter == line.at(0)) {
parts.push_back({});
}
for (const std::string::value_type& c : line) {
if (
(
c == delimiter
&&
(skipEmpty ? (!parts.empty() && !parts.back().empty()) : true)
)
||
(c != delimiter && parts.empty())
) {
parts.push_back({});
}
if (c != delimiter) {
parts.back().push_back(c);
}
}
if (skipEmpty && !parts.empty() && parts.back().empty()) {
parts.pop_back();
}
return parts;
}
void test(const std::string& line) {
std::cout << line << std::endl;
std::cout << "skipEmpty=0 |";
for (const std::string& part : split(line, ':')) {
std::cout << part << '|';
}
std::cout << std::endl;
std::cout << "skipEmpty=1 |";
for (const std::string& part : split(line, ':', true)) {
std::cout << part << '|';
}
std::cout << std::endl;
std::cout << std::endl;
}
int main() {
test("foo:bar:::baz");
test("");
test("foo");
test(":");
test("::");
test(":foo");
test("::foo");
test(":foo:");
test(":foo::");
return 0;
}
Output:
foo:bar:::baz
skipEmpty=0 |foo|bar|||baz|
skipEmpty=1 |foo|bar|baz|
skipEmpty=0 |
skipEmpty=1 |
foo
skipEmpty=0 |foo|
skipEmpty=1 |foo|
:
skipEmpty=0 |||
skipEmpty=1 |
::
skipEmpty=0 ||||
skipEmpty=1 |
:foo
skipEmpty=0 ||foo|
skipEmpty=1 |foo|
::foo
skipEmpty=0 |||foo|
skipEmpty=1 |foo|
:foo:
skipEmpty=0 ||foo||
skipEmpty=1 |foo|
:foo::
skipEmpty=0 ||foo|||
skipEmpty=1 |foo|
The stringstream can be convenient if you need to parse the string by non-space symbols:
string s = "Name:JAck; Spouse:Susan; ...";
string dummy, name, spouse;
istringstream iss(s);
getline(iss, dummy, ':');
getline(iss, name, ';');
getline(iss, dummy, ':');
getline(iss, spouse, ';')
The STL does not have such a method available already.
However, you can either use C's strtok() function by using the std::string::c_str() member, or you can write your own. Here is a code sample I found after a quick Google search ("STL string split"):
void Tokenize(const string& str,
vector<string>& tokens,
const string& delimiters = " ")
{
// Skip delimiters at beginning.
string::size_type lastPos = str.find_first_not_of(delimiters, 0);
// Find first "non-delimiter".
string::size_type pos = str.find_first_of(delimiters, lastPos);
while (string::npos != pos || string::npos != lastPos)
{
// Found a token, add it to the vector.
tokens.push_back(str.substr(lastPos, pos - lastPos));
// Skip delimiters. Note the "not_of"
lastPos = str.find_first_not_of(delimiters, pos);
// Find next "non-delimiter"
pos = str.find_first_of(delimiters, lastPos);
}
}
Taken from: http://oopweb.com/CPP/Documents/CPPHOWTO/Volume/C++Programming-HOWTO-7.html
If you have questions about the code sample, leave a comment and I will explain.
And just because it does not implement a typedef called iterator or overload the << operator does not mean it is bad code. I use C functions quite frequently. For example, printf and scanf both are faster than std::cin and std::cout (significantly), the fopen syntax is a lot more friendly for binary types, and they also tend to produce smaller EXEs.
Don't get sold on this "Elegance over performance" deal.
Here is a split function that:
ignores empty tokens (can easily be changed)
template<typename T>
vector<T>
split(const T & str, const T & delimiters) {
vector<T> v;
typename T::size_type start = 0;
auto pos = str.find_first_of(delimiters, start);
while(pos != T::npos) {
if(pos != start) // ignore empty tokens
v.emplace_back(str, start, pos - start);
start = pos + 1;
pos = str.find_first_of(delimiters, start);
}
if(start < str.length()) // ignore trailing delimiter
v.emplace_back(str, start, str.length() - start); // add what's left of the string
return v;
}
Example usage:
vector<string> v = split<string>("Hello, there; World", ";,");
vector<wstring> v = split<wstring>(L"Hello, there; World", L";,");
#include <iostream>
#include <string>
#include <sstream>
#include <algorithm>
#include <iterator>
#include <vector>
int main() {
using namespace std;
int n=8;
string sentence = "10 20 30 40 5 6 7 8";
istringstream iss(sentence);
vector<string> tokens;
copy(istream_iterator<string>(iss),
istream_iterator<string>(),
back_inserter(tokens));
for(int i=0;i<n;i++){
cout<<tokens.at(i);
}
}
I use this to split string by a delimiter. The first puts the results in a pre-constructed vector, the second returns a new vector.
#include <string>
#include <sstream>
#include <vector>
#include <iterator>
template <typename Out>
void split(const std::string &s, char delim, Out result) {
std::istringstream iss(s);
std::string item;
while (std::getline(iss, item, delim)) {
*result++ = item;
}
}
std::vector<std::string> split(const std::string &s, char delim) {
std::vector<std::string> elems;
split(s, delim, std::back_inserter(elems));
return elems;
}
Note that this solution does not skip empty tokens, so the following will find 4 items, one of which is empty:
std::vector<std::string> x = split("one:two::three", ':');
#include <iostream>
#include <string>
#include <deque>
std::deque<std::string> split(
const std::string& line,
std::string::value_type delimiter,
bool skipEmpty = false
) {
std::deque<std::string> parts{};
if (!skipEmpty && !line.empty() && delimiter == line.at(0)) {
parts.push_back({});
}
for (const std::string::value_type& c : line) {
if (
(
c == delimiter
&&
(skipEmpty ? (!parts.empty() && !parts.back().empty()) : true)
)
||
(c != delimiter && parts.empty())
) {
parts.push_back({});
}
if (c != delimiter) {
parts.back().push_back(c);
}
}
if (skipEmpty && !parts.empty() && parts.back().empty()) {
parts.pop_back();
}
return parts;
}
void test(const std::string& line) {
std::cout << line << std::endl;
std::cout << "skipEmpty=0 |";
for (const std::string& part : split(line, ':')) {
std::cout << part << '|';
}
std::cout << std::endl;
std::cout << "skipEmpty=1 |";
for (const std::string& part : split(line, ':', true)) {
std::cout << part << '|';
}
std::cout << std::endl;
std::cout << std::endl;
}
int main() {
test("foo:bar:::baz");
test("");
test("foo");
test(":");
test("::");
test(":foo");
test("::foo");
test(":foo:");
test(":foo::");
return 0;
}
Output:
foo:bar:::baz
skipEmpty=0 |foo|bar|||baz|
skipEmpty=1 |foo|bar|baz|
skipEmpty=0 |
skipEmpty=1 |
foo
skipEmpty=0 |foo|
skipEmpty=1 |foo|
:
skipEmpty=0 |||
skipEmpty=1 |
::
skipEmpty=0 ||||
skipEmpty=1 |
:foo
skipEmpty=0 ||foo|
skipEmpty=1 |foo|
::foo
skipEmpty=0 |||foo|
skipEmpty=1 |foo|
:foo:
skipEmpty=0 ||foo||
skipEmpty=1 |foo|
:foo::
skipEmpty=0 ||foo|||
skipEmpty=1 |foo|
A possible solution using Boost might be:
#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));
This approach might be even faster than the stringstream approach. And since this is a generic template function it can be used to split other types of strings (wchar, etc. or UTF-8) using all kinds of delimiters.
See the documentation for details.
Yes, I looked through all 30 examples.
I couldn't find a version of split that works for multi-char delimiters, so here's mine:
#include <string>
#include <vector>
using namespace std;
vector<string> split(const string &str, const string &delim)
{
const auto delim_pos = str.find(delim);
if (delim_pos == string::npos)
return {str};
vector<string> ret{str.substr(0, delim_pos)};
auto tail = split(str.substr(delim_pos + delim.size(), string::npos), delim);
ret.insert(ret.end(), tail.begin(), tail.end());
return ret;
}
Probably not the most efficient of implementations, but it's a very straightforward recursive solution, using only <string> and <vector>.
Ah, it's written in C++11, but there's nothing special about this code, so you could easily adapt it to C++98.
Here is my solution using C++11 and the STL. It should be reasonably efficient:
#include <vector>
#include <string>
#include <cstring>
#include <iostream>
#include <algorithm>
#include <functional>
std::vector<std::string> split(const std::string& s)
{
std::vector<std::string> v;
const auto end = s.end();
auto to = s.begin();
decltype(to) from;
while((from = std::find_if(to, end,
[](char c){ return !std::isspace(c); })) != end)
{
to = std::find_if(from, end, [](char c){ return std::isspace(c); });
v.emplace_back(from, to);
}
return v;
}
int main()
{
std::string s = "this is the string to split";
auto v = split(s);
for(auto&& s: v)
std::cout << s << '\n';
}
Output:
this
is
the
string
to
split
if you want split string by some chars you can use
#include<iostream>
#include<string>
#include<vector>
#include<iterator>
#include<sstream>
#include<string>
using namespace std;
void replaceOtherChars(string &input, vector<char> ÷rs)
{
const char divider = dividers.at(0);
int replaceIndex = 0;
vector<char>::iterator it_begin = dividers.begin()+1,
it_end= dividers.end();
for(;it_begin!=it_end;++it_begin)
{
replaceIndex = 0;
while(true)
{
replaceIndex=input.find_first_of(*it_begin,replaceIndex);
if(replaceIndex==-1)
break;
input.at(replaceIndex)=divider;
}
}
}
vector<string> split(string str, vector<char> chars, bool missEmptySpace =true )
{
vector<string> result;
const char divider = chars.at(0);
replaceOtherChars(str,chars);
stringstream stream;
stream<<str;
string temp;
while(getline(stream,temp,divider))
{
if(missEmptySpace && temp.empty())
continue;
result.push_back(temp);
}
return result;
}
int main()
{
string str ="milk, pigs.... hot-dogs ";
vector<char> arr;
arr.push_back(' '); arr.push_back(','); arr.push_back('.');
vector<string> result = split(str,arr);
vector<string>::iterator it_begin= result.begin(),
it_end= result.end();
for(;it_begin!=it_end;++it_begin)
{
cout<<*it_begin<<endl;
}
return 0;
}
I use the following
void split(string in, vector<string>& parts, char separator) {
string::iterator ts, curr;
ts = curr = in.begin();
for(; curr <= in.end(); curr++ ) {
if( (curr == in.end() || *curr == separator) && curr > ts )
parts.push_back( string( ts, curr ));
if( curr == in.end() )
break;
if( *curr == separator ) ts = curr + 1;
}
}
PlasmaHH, I forgot to include the extra check( curr > ts) for removing tokens with whitespace.
I like to use the boost/regex methods for this task since they provide maximum flexibility for specifying the splitting criteria.
#include <iostream>
#include <string>
#include <boost/regex.hpp>
int main() {
std::string line("A:::line::to:split");
const boost::regex re(":+"); // one or more colons
// -1 means find inverse matches aka split
boost::sregex_token_iterator tokens(line.begin(),line.end(),re,-1);
boost::sregex_token_iterator end;
for (; tokens != end; ++tokens)
std::cout << *tokens << std::endl;
}
very late to the party here I know but I was thinking about the most elegant way of doing this if you were given a range of delimiters rather than whitespace, and using nothing more than the standard library.
Here are my thoughts:
To split words into a string vector by a sequence of delimiters:
template<class Container>
std::vector<std::string> split_by_delimiters(const std::string& input, const Container& delimiters)
{
std::vector<std::string> result;
for (auto current = begin(input) ; current != end(input) ; )
{
auto first = find_if(current, end(input), not_in(delimiters));
if (first == end(input)) break;
auto last = find_if(first, end(input), is_in(delimiters));
result.emplace_back(first, last);
current = last;
}
return result;
}
to split the other way, by providing a sequence of valid characters:
template<class Container>
std::vector<std::string> split_by_valid_chars(const std::string& input, const Container& valid_chars)
{
std::vector<std::string> result;
for (auto current = begin(input) ; current != end(input) ; )
{
auto first = find_if(current, end(input), is_in(valid_chars));
if (first == end(input)) break;
auto last = find_if(first, end(input), not_in(valid_chars));
result.emplace_back(first, last);
current = last;
}
return result;
}
is_in and not_in are defined thus:
namespace detail {
template<class Container>
struct is_in {
is_in(const Container& charset)
: _charset(charset)
{}
bool operator()(char c) const
{
return find(begin(_charset), end(_charset), c) != end(_charset);
}
const Container& _charset;
};
template<class Container>
struct not_in {
not_in(const Container& charset)
: _charset(charset)
{}
bool operator()(char c) const
{
return find(begin(_charset), end(_charset), c) == end(_charset);
}
const Container& _charset;
};
}
template<class Container>
detail::not_in<Container> not_in(const Container& c)
{
return detail::not_in<Container>(c);
}
template<class Container>
detail::is_in<Container> is_in(const Container& c)
{
return detail::is_in<Container>(c);
}
Here's another way of doing it..
void split_string(string text,vector<string>& words)
{
int i=0;
char ch;
string word;
while(ch=text[i++])
{
if (isspace(ch))
{
if (!word.empty())
{
words.push_back(word);
}
word = "";
}
else
{
word += ch;
}
}
if (!word.empty())
{
words.push_back(word);
}
}
// adapted from a "regular" csv parse
std::string stringIn = "my csv is 10233478 NOTseparated by commas";
std::vector<std::string> commaSeparated(1);
int commaCounter = 0;
for (int i=0; i<stringIn.size(); i++) {
if (stringIn[i] == " ") {
commaSeparated.push_back("");
commaCounter++;
} else {
commaSeparated.at(commaCounter) += stringIn[i];
}
}
in the end you will have a vector of strings with every element in the sentence separated by spaces. only non-standard resource is std::vector (but since an std::string is involved, i figured it would be acceptable).
empty strings are saved as a separate items.
Not that we need more answers, but this is what I came up with after being inspired by Evan Teran.
std::vector <std::string> split(const string &input, auto delimiter, bool skipEmpty=true) {
/*
Splits a string at each delimiter and returns these strings as a string vector.
If the delimiter is not found then nothing is returned.
If skipEmpty is true then strings between delimiters that are 0 in length will be skipped.
*/
bool delimiterFound = false;
int pos=0, pPos=0;
std::vector <std::string> result;
while (true) {
pos = input.find(delimiter,pPos);
if (pos != std::string::npos) {
if (skipEmpty==false or pos-pPos > 0) // if empty values are to be kept or not
result.push_back(input.substr(pPos,pos-pPos));
delimiterFound = true;
} else {
if (pPos < input.length() and delimiterFound) {
if (skipEmpty==false or input.length()-pPos > 0) // if empty values are to be kept or not
result.push_back(input.substr(pPos,input.length()-pPos));
}
break;
}
pPos = pos+1;
}
return result;
}
Quick version which uses vector as the base class, giving full access to all of its operators:
// Split string into parts.
class Split : public std::vector<std::string>
{
public:
Split(const std::string& str, char* delimList)
{
size_t lastPos = 0;
size_t pos = str.find_first_of(delimList);
while (pos != std::string::npos)
{
if (pos != lastPos)
push_back(str.substr(lastPos, pos-lastPos));
lastPos = pos + 1;
pos = str.find_first_of(delimList, lastPos);
}
if (lastPos < str.length())
push_back(str.substr(lastPos, pos-lastPos));
}
};
Example used to populate an STL set:
std::set<std::string> words;
Split split("Hello,World", ",");
words.insert(split.begin(), split.end());
I've been searching for a way to split a string by a separator of any length, so I started writing it from scratch, as existing solutions didn't suit me.
Here is my little algorithm, using only STL:
//use like this
//std::vector<std::wstring> vec = Split<std::wstring> (L"Hello##world##!", L"##");
template <typename valueType>
static std::vector <valueType> Split (valueType text, const valueType& delimiter)
{
std::vector <valueType> tokens;
size_t pos = 0;
valueType token;
while ((pos = text.find(delimiter)) != valueType::npos)
{
token = text.substr(0, pos);
tokens.push_back (token);
text.erase(0, pos + delimiter.length());
}
tokens.push_back (text);
return tokens;
}
It can be used with separator of any length and form, as far as I've tested. Instantiate with either string or wstring type.
All the algorithm does is it searches for the delimiter, gets the part of the string that is up to the delimiter, deletes the delimiter and searches again until it finds it no more.
Of course, you can use any number of whitespaces for the delimiter.
I hope it helps.
my general implementation for string and u32string ~, using the boost::algorithm::split signature.
template<typename CharT, typename UnaryPredicate>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
UnaryPredicate predicate)
{
using ST = std::basic_string<CharT>;
using std::swap;
std::vector<ST> tmp_result;
auto iter = s.cbegin(),
end_iter = s.cend();
while (true)
{
/**
* edge case: empty str -> push an empty str and exit.
*/
auto find_iter = find_if(iter, end_iter, predicate);
tmp_result.emplace_back(iter, find_iter);
if (find_iter == end_iter) { break; }
iter = ++find_iter;
}
swap(tmp_result, split_result);
}
template<typename CharT>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
const std::basic_string<CharT>& char_candidate)
{
std::unordered_set<CharT> candidate_set(char_candidate.cbegin(),
char_candidate.cend());
auto predicate = [&candidate_set](const CharT& c) {
return candidate_set.count(c) > 0U;
};
return split(split_result, s, predicate);
}
template<typename CharT>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
const CharT* literals)
{
return split(split_result, s, std::basic_string<CharT>(literals));
}
Heres a regex solution that only uses the standard regex library. (I'm a little rusty, so there may be a few syntax errors, but this is at least the general idea)
#include <regex.h>
#include <string.h>
#include <vector.h>
using namespace std;
vector<string> split(string s){
regex r ("\\w+"); //regex matches whole words, (greedy, so no fragment words)
regex_iterator<string::iterator> rit ( s.begin(), s.end(), r );
regex_iterator<string::iterator> rend; //iterators to iterate thru words
vector<string> result<regex_iterator>(rit, rend);
return result; //iterates through the matches to fill the vector
}
Short and elegant
#include <vector>
#include <string>
using namespace std;
vector<string> split(string data, string token)
{
vector<string> output;
size_t pos = string::npos; // size_t to avoid improbable overflow
do
{
pos = data.find(token);
output.push_back(data.substr(0, pos));
if (string::npos != pos)
data = data.substr(pos + token.size());
} while (string::npos != pos);
return output;
}
can use any string as delimiter, also can be used with binary data (std::string supports binary data, including nulls)
using:
auto a = split("this!!is!!!example!string", "!!");
output:
this
is
!example!string
Quick version which uses vector as the base class, giving full access to all of its operators:
// Split string into parts.
class Split : public std::vector<std::string>
{
public:
Split(const std::string& str, char* delimList)
{
size_t lastPos = 0;
size_t pos = str.find_first_of(delimList);
while (pos != std::string::npos)
{
if (pos != lastPos)
push_back(str.substr(lastPos, pos-lastPos));
lastPos = pos + 1;
pos = str.find_first_of(delimList, lastPos);
}
if (lastPos < str.length())
push_back(str.substr(lastPos, pos-lastPos));
}
};
Example used to populate an STL set:
std::set<std::string> words;
Split split("Hello,World", ",");
words.insert(split.begin(), split.end());
Not that we need more answers, but this is what I came up with after being inspired by Evan Teran.
std::vector <std::string> split(const string &input, auto delimiter, bool skipEmpty=true) {
/*
Splits a string at each delimiter and returns these strings as a string vector.
If the delimiter is not found then nothing is returned.
If skipEmpty is true then strings between delimiters that are 0 in length will be skipped.
*/
bool delimiterFound = false;
int pos=0, pPos=0;
std::vector <std::string> result;
while (true) {
pos = input.find(delimiter,pPos);
if (pos != std::string::npos) {
if (skipEmpty==false or pos-pPos > 0) // if empty values are to be kept or not
result.push_back(input.substr(pPos,pos-pPos));
delimiterFound = true;
} else {
if (pPos < input.length() and delimiterFound) {
if (skipEmpty==false or input.length()-pPos > 0) // if empty values are to be kept or not
result.push_back(input.substr(pPos,input.length()-pPos));
}
break;
}
pPos = pos+1;
}
return result;
}
This is my solution to this problem:
vector<string> get_tokens(string str) {
vector<string> dt;
stringstream ss;
string tmp;
ss << str;
for (size_t i; !ss.eof(); ++i) {
ss >> tmp;
dt.push_back(tmp);
}
return dt;
}
This function returns a vector of strings.
As a hobbyist, this is the first solution that came to my mind. I'm kind of curious why I haven't seen a similar solution here yet, is there something fundamentally wrong with how I did it?
#include <iostream>
#include <string>
#include <vector>
std::vector<std::string> split(const std::string &s, const std::string &delims)
{
std::vector<std::string> result;
std::string::size_type pos = 0;
while (std::string::npos != (pos = s.find_first_not_of(delims, pos))) {
auto pos2 = s.find_first_of(delims, pos);
result.emplace_back(s.substr(pos, std::string::npos == pos2 ? pos2 : pos2 - pos));
pos = pos2;
}
return result;
}
int main()
{
std::string text{"And then I said: \"I don't get it, why would you even do that!?\""};
std::string delims{" :;\".,?!"};
auto words = split(text, delims);
std::cout << "\nSentence:\n " << text << "\n\nWords:";
for (const auto &w : words) {
std::cout << "\n " << w;
}
return 0;
}
This answer takes the string and puts it into a vector of strings. It uses the boost library.
#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));
A possible solution using Boost might be:
#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));
This approach might be even faster than the stringstream approach. And since this is a generic template function it can be used to split other types of strings (wchar, etc. or UTF-8) using all kinds of delimiters.
See the documentation for details.
I use this simpleton because we got our String class "special" (i.e. not standard):
void splitString(const String &s, const String &delim, std::vector<String> &result) {
const int l = delim.length();
int f = 0;
int i = s.indexOf(delim,f);
while (i>=0) {
String token( i-f > 0 ? s.substring(f,i-f) : "");
result.push_back(token);
f=i+l;
i = s.indexOf(delim,f);
}
String token = s.substring(f);
result.push_back(token);
}
My code is:
#include <list>
#include <string>
template<class StringType = std::string, class ContainerType = std::list<StringType> >
class DSplitString:public ContainerType
{
public:
explicit DSplitString(const StringType& strString, char cChar, bool bSkipEmptyParts = true)
{
size_t iPos = 0;
size_t iPos_char = 0;
while(StringType::npos != (iPos_char = strString.find(cChar, iPos)))
{
StringType strTemp = strString.substr(iPos, iPos_char - iPos);
if((bSkipEmptyParts && !strTemp.empty()) || (!bSkipEmptyParts))
push_back(strTemp);
iPos = iPos_char + 1;
}
}
explicit DSplitString(const StringType& strString, const StringType& strSub, bool bSkipEmptyParts = true)
{
size_t iPos = 0;
size_t iPos_char = 0;
while(StringType::npos != (iPos_char = strString.find(strSub, iPos)))
{
StringType strTemp = strString.substr(iPos, iPos_char - iPos);
if((bSkipEmptyParts && !strTemp.empty()) || (!bSkipEmptyParts))
push_back(strTemp);
iPos = iPos_char + strSub.length();
}
}
};
Example:
#include <iostream>
#include <string>
int _tmain(int argc, _TCHAR* argv[])
{
DSplitString<> aa("doicanhden1;doicanhden2;doicanhden3;", ';');
for each (std::string var in aa)
{
std::cout << var << std::endl;
}
std::cin.get();
return 0;
}
Loop on getline with ' ' as the token.
Here's another solution. It's compact and reasonably efficient:
std::vector<std::string> split(const std::string &text, char sep) {
std::vector<std::string> tokens;
std::size_t start = 0, end = 0;
while ((end = text.find(sep, start)) != std::string::npos) {
tokens.push_back(text.substr(start, end - start));
start = end + 1;
}
tokens.push_back(text.substr(start));
return tokens;
}
It can easily be templatised to handle string separators, wide strings, etc.
Note that splitting "" results in a single empty string and splitting "," (ie. sep) results in two empty strings.
It can also be easily expanded to skip empty tokens:
std::vector<std::string> split(const std::string &text, char sep) {
std::vector<std::string> tokens;
std::size_t start = 0, end = 0;
while ((end = text.find(sep, start)) != std::string::npos) {
if (end != start) {
tokens.push_back(text.substr(start, end - start));
}
start = end + 1;
}
if (end != start) {
tokens.push_back(text.substr(start));
}
return tokens;
}
If splitting a string at multiple delimiters while skipping empty tokens is desired, this version may be used:
std::vector<std::string> split(const std::string& text, const std::string& delims)
{
std::vector<std::string> tokens;
std::size_t start = text.find_first_not_of(delims), end = 0;
while((end = text.find_first_of(delims, start)) != std::string::npos)
{
tokens.push_back(text.substr(start, end - start));
start = text.find_first_not_of(delims, end);
}
if(start != std::string::npos)
tokens.push_back(text.substr(start));
return tokens;
}
I use this simpleton because we got our String class "special" (i.e. not standard):
void splitString(const String &s, const String &delim, std::vector<String> &result) {
const int l = delim.length();
int f = 0;
int i = s.indexOf(delim,f);
while (i>=0) {
String token( i-f > 0 ? s.substring(f,i-f) : "");
result.push_back(token);
f=i+l;
i = s.indexOf(delim,f);
}
String token = s.substring(f);
result.push_back(token);
}
#include<iostream>
#include<string>
#include<sstream>
#include<vector>
using namespace std;
vector<string> split(const string &s, char delim) {
vector<string> elems;
stringstream ss(s);
string item;
while (getline(ss, item, delim)) {
elems.push_back(item);
}
return elems;
}
int main() {
vector<string> x = split("thi is an sample test",' ');
unsigned int i;
for(i=0;i<x.size();i++)
cout<<i<<":"<<x[i]<<endl;
return 0;
}
Based on Galik's answer I made this. This is mostly here so I don't have to keep writing it again and again. It's crazy that C++ still doesn't have a native split function. Features:
"\r\n")#include <string>
#include <vector>
#include <algorithm>
std::vector<std::string> split(const std::string& s, const std::string& delims)
{
using namespace std;
vector<string> v;
// Start of an element.
size_t elemStart = 0;
// We start searching from the end of the previous element, which
// initially is the start of the string.
size_t elemEnd = 0;
// Find the first non-delim, i.e. the start of an element, after the end of the previous element.
while((elemStart = s.find_first_not_of(delims, elemEnd)) != string::npos)
{
// Find the first delem, i.e. the end of the element (or if this fails it is the end of the string).
elemEnd = s.find_first_of(delims, elemStart);
// Add it.
v.emplace_back(s, elemStart, elemEnd == string::npos ? string::npos : elemEnd - elemStart);
}
// When there are no more non-spaces, we are done.
return v;
}
Just for convenience:
template<class V, typename T>
bool in(const V &v, const T &el) {
return std::find(v.begin(), v.end(), el) != v.end();
}
The actual splitting based on multiple delimiters:
std::vector<std::string> split(const std::string &s,
const std::vector<char> &delims) {
std::vector<std::string> res;
auto stuff = [&delims](char c) { return !in(delims, c); };
auto space = [&delims](char c) { return in(delims, c); };
auto first = std::find_if(s.begin(), s.end(), stuff);
while (first != s.end()) {
auto last = std::find_if(first, s.end(), space);
res.push_back(std::string(first, last));
first = std::find_if(last + 1, s.end(), stuff);
}
return res;
}
The usage:
int main() {
std::string s = " aaa, bb cc ";
for (auto el: split(s, {' ', ','}))
std::cout << el << std::endl;
return 0;
}
C++17 version without any memory allocation (except may be for std::function)
void iter_words(const std::string_view& input, const std::function<void(std::string_view)>& process_word) {
auto itr = input.begin();
auto consume_whitespace = [&]() {
for(; itr != input.end(); ++itr) {
if(!isspace(*itr))
return;
}
};
auto consume_letters = [&]() {
for(; itr != input.end(); ++itr) {
if(isspace(*itr))
return;
}
};
while(true) {
consume_whitespace();
if(itr == input.end())
return;
auto word_start = itr - input.begin();
consume_letters();
auto word_end = itr - input.begin();
process_word(input.substr(word_start, word_end - word_start));
}
}
int main() {
iter_words("foo bar", [](std::string_view sv) {
std::cout << "Got word: " << sv << '\n';
});
return 0;
}
Source: Stackoverflow.com