When the input string is blank, boost::split
returns a vector with one empty string in it.
Is it possible to have boost::split
return 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();
}
Output:
1
Desired output:
0
Compression compresses adjacent delimiters, it does not avoid empty tokens.
If you consider the following, you can see why this works consistently:
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, '\'') << " ";
}
}
Prints
=== TEST: === ''
=== TEST: token === 'token'
=== TEST: , === '' ''
=== TEST: token, === 'token' ''
=== TEST: ,token === '' 'token'
=== TEST: ,, === '' ''
=== TEST: ,token, === '' 'token' ''
=== TEST: ,,token === '' 'token'
=== TEST: token,, === 'token' ''
So, you might fix it by trimming delimiters from front and end and checking that the remaining input is non-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, '\'') << " ";
}
}
Printing:
=== TEST: ===
=== TEST: token === 'token'
=== TEST: , ===
=== TEST: token, === 'token'
=== TEST: ,token === 'token'
=== TEST: ,, ===
=== TEST: ,token, === 'token'
=== TEST: ,,token === 'token'
=== TEST: token,, === 'token'
Using Spirit X3, seems to me to be 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, '\'') << " ";
}
}
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With