Boost :: split pushes an empty string into a vector even with token_compress_on

Question

When the input line is empty, boost::splitreturns a vector with one empty line in it.

Is it possible to boost::splitreturn an empty vector instead ?

MCVE:

#include <string>
#include <vector>
#include <boost/algorithm/string.hpp>

int main() {
    std::vector<std::string> result;
    boost::split(result, "", boost::is_any_of(","), boost::algorithm::token_compress_on);
    std::cout << result.size();
}

Conclusion:

1

Required Conclusion:

0

Answer 1

Compression compresses adjacent delimiters; it does not exclude empty tokens.

If you consider the following, you can understand why this works sequentially:

Live On Coliru

#include <boost/algorithm/string.hpp>
#include <string>
#include <iostream>
#include <iomanip>
#include <vector>

int main() {
    for (std::string const& test : {
            "", "token", 
            ",", "token,", ",token", 
            ",,", ",token,", ",,token", "token,,"
        })
    {
        std::vector<std::string> result;
        boost::split(result, test, boost::is_any_of(","), boost::algorithm::token_compress_on);
        std::cout << "\n=== TEST: " << std::left << std::setw(8) << test << " === ";
        for (auto& tok : result)
            std::cout << std::quoted(tok, '\'') << " ";
    }
}

Print

=== TEST:          === '' 
=== TEST: token    === 'token' 
=== TEST: ,        === '' '' 
=== TEST: token,   === 'token' '' 
=== TEST: ,token   === '' 'token' 
=== TEST: ,,       === '' '' 
=== TEST: ,token,  === '' 'token' '' 
=== TEST: ,,token  === '' 'token' 
=== TEST: token,,  === 'token' '' 

So, you can fix this by trimming the delimiters from the front and from the end and checking that the remaining input is not empty:

Live On Coliru

#include <boost/algorithm/string.hpp>
#include <boost/utility/string_view.hpp>
#include <string>
#include <iostream>
#include <iomanip>
#include <vector>

int main() {
    auto const delim = boost::is_any_of(",");

    for (std::string test : {
            "", "token", 
            ",", "token,", ",token", 
            ",,", ",token,", ",,token", "token,,"
        })
    {
        std::cout << "\n=== TEST: " << std::left << std::setw(8) << test << " === ";

        std::vector<std::string> result;

        boost::trim_if(test, delim);
        if (!test.empty())
            boost::split(result, test, delim, boost::algorithm::token_compress_on);

        for (auto& tok : result)
            std::cout << std::quoted(tok, '\'') << " ";
    }
}

Print

=== TEST:          === 
=== TEST: token    === 'token' 
=== TEST: ,        === 
=== TEST: token,   === 'token' 
=== TEST: ,token   === 'token' 
=== TEST: ,,       === 
=== TEST: ,token,  === 'token' 
=== TEST: ,,token  === 'token' 
=== TEST: token,,  === 'token' 

BONUS: Boost Spirit

Using Spirit X3 seems to me more flexible and potentially more efficient:

Live On Coliru

#include <boost/spirit/home/x3.hpp>
#include <string>
#include <iostream>
#include <iomanip>
#include <vector>

int main() {
    static auto const delim = boost::spirit::x3::char_(",");

    for (std::string test : {
            "", "token", 
            ",", "token,", ",token", 
            ",,", ",token,", ",,token", "token,,"
        })
    {
        std::cout << "\n=== TEST: " << std::left << std::setw(8) << test << " === ";

        std::vector<std::string> result;
        parse(test.begin(), test.end(), -(+~delim) % delim, result);

        for (auto& tok : result)
            std::cout << std::quoted(tok, '\'') << " ";
    }
}