Java有一个方便的分割方法:
String str = "The quick brown fox";
String[] results = str.split(" ");
在c++中有简单的方法来做到这一点吗?
当前回答
我只是看了所有的答案，找不到下一个前提条件的解决方案:
没有动态内存分配 不使用boost 不使用正则表达式 c++17标准
这就是我的解
#include <iomanip>
#include <iostream>
#include <iterator>
#include <string_view>
#include <utility>
struct split_by_spaces
{
std::string_view text;
static constexpr char delim = ' ';
struct iterator
{
const std::string_view& text;
std::size_t cur_pos;
std::size_t end_pos;
std::string_view operator*() const
{
return { &text[cur_pos], end_pos - cur_pos };
}
bool operator==(const iterator& other) const
{
return cur_pos == other.cur_pos && end_pos == other.end_pos;
}
bool operator!=(const iterator& other) const
{
return !(*this == other);
}
iterator& operator++()
{
cur_pos = text.find_first_not_of(delim, end_pos);
if (cur_pos == std::string_view::npos)
{
cur_pos = text.size();
end_pos = cur_pos;
return *this;
}
end_pos = text.find(delim, cur_pos);
if (cur_pos == std::string_view::npos)
{
end_pos = text.size();
}
return *this;
}
};
[[nodiscard]] iterator begin() const
{
auto start = text.find_first_not_of(delim);
if (start == std::string_view::npos)
{
return iterator{ text, text.size(), text.size() };
}
auto end_word = text.find(delim, start);
if (end_word == std::string_view::npos)
{
end_word = text.size();
}
return iterator{ text, start, end_word };
}
[[nodiscard]] iterator end() const
{
return iterator{ text, text.size(), text.size() };
}
};
int main(int argc, char** argv)
{
using namespace std::literals;
auto str = " there should be no memory allocation during parsing"
" into words this line and you should'n create any"
" contaner for intermediate words "sv;
auto comma = "";
for (std::string_view word : split_by_spaces{ str })
{
std::cout << std::exchange(comma, ",") << std::quoted(word);
}
auto only_spaces = " "sv;
for (std::string_view word : split_by_spaces{ only_spaces })
{
std::cout << "you will not see this line in output" << std::endl;
}
}
其他回答
这是一个非常简单的问题:
#include <vector>
#include <string>
using namespace std;
vector<string> split(const char *str, char c = ' ')
{
vector<string> result;
do
{
const char *begin = str;
while(*str != c && *str)
str++;
result.push_back(string(begin, str));
} while (0 != *str++);
return result;
}
你可以利用boost::make_find_iterator。类似于这个:
template<typename CH>
inline vector< basic_string<CH> > tokenize(
const basic_string<CH> &Input,
const basic_string<CH> &Delimiter,
bool remove_empty_token
) {
typedef typename basic_string<CH>::const_iterator string_iterator_t;
typedef boost::find_iterator< string_iterator_t > string_find_iterator_t;
vector< basic_string<CH> > Result;
string_iterator_t it = Input.begin();
string_iterator_t it_end = Input.end();
for(string_find_iterator_t i = boost::make_find_iterator(Input, boost::first_finder(Delimiter, boost::is_equal()));
i != string_find_iterator_t();
++i) {
if(remove_empty_token){
if(it != i->begin())
Result.push_back(basic_string<CH>(it,i->begin()));
}
else
Result.push_back(basic_string<CH>(it,i->begin()));
it = i->end();
}
if(it != it_end)
Result.push_back(basic_string<CH>(it,it_end));
return Result;
}
Boost标记器类可以使这类事情变得非常简单:
#include <iostream>
#include <string>
#include <boost/foreach.hpp>
#include <boost/tokenizer.hpp>
using namespace std;
using namespace boost;
int main(int, char**)
{
string text = "token, test string";
char_separator<char> sep(", ");
tokenizer< char_separator<char> > tokens(text, sep);
BOOST_FOREACH (const string& t, tokens) {
cout << t << "." << endl;
}
}
针对c++ 11更新:
#include <iostream>
#include <string>
#include <boost/tokenizer.hpp>
using namespace std;
using namespace boost;
int main(int, char**)
{
string text = "token, test string";
char_separator<char> sep(", ");
tokenizer<char_separator<char>> tokens(text, sep);
for (const auto& t : tokens) {
cout << t << "." << endl;
}
}
简单的c++代码(标准c++ 98)，接受多个分隔符(在std::string中指定)，只使用向量、字符串和迭代器。
#include <iostream>
#include <vector>
#include <string>
#include <stdexcept>
std::vector<std::string>
split(const std::string& str, const std::string& delim){
std::vector<std::string> result;
if (str.empty())
throw std::runtime_error("Can not tokenize an empty string!");
std::string::const_iterator begin, str_it;
begin = str_it = str.begin();
do {
while (delim.find(*str_it) == std::string::npos && str_it != str.end())
str_it++; // find the position of the first delimiter in str
std::string token = std::string(begin, str_it); // grab the token
if (!token.empty()) // empty token only when str starts with a delimiter
result.push_back(token); // push the token into a vector<string>
while (delim.find(*str_it) != std::string::npos && str_it != str.end())
str_it++; // ignore the additional consecutive delimiters
begin = str_it; // process the remaining tokens
} while (str_it != str.end());
return result;
}
int main() {
std::string test_string = ".this is.a.../.simple;;test;;;END";
std::string delim = "; ./"; // string containing the delimiters
std::vector<std::string> tokens = split(test_string, delim);
for (std::vector<std::string>::const_iterator it = tokens.begin();
it != tokens.end(); it++)
std::cout << *it << std::endl;
}
我只是看了所有的答案，找不到下一个前提条件的解决方案:
没有动态内存分配 不使用boost 不使用正则表达式 c++17标准
这就是我的解
#include <iomanip>
#include <iostream>
#include <iterator>
#include <string_view>
#include <utility>
struct split_by_spaces
{
std::string_view text;
static constexpr char delim = ' ';
struct iterator
{
const std::string_view& text;
std::size_t cur_pos;
std::size_t end_pos;
std::string_view operator*() const
{
return { &text[cur_pos], end_pos - cur_pos };
}
bool operator==(const iterator& other) const
{
return cur_pos == other.cur_pos && end_pos == other.end_pos;
}
bool operator!=(const iterator& other) const
{
return !(*this == other);
}
iterator& operator++()
{
cur_pos = text.find_first_not_of(delim, end_pos);
if (cur_pos == std::string_view::npos)
{
cur_pos = text.size();
end_pos = cur_pos;
return *this;
}
end_pos = text.find(delim, cur_pos);
if (cur_pos == std::string_view::npos)
{
end_pos = text.size();
}
return *this;
}
};
[[nodiscard]] iterator begin() const
{
auto start = text.find_first_not_of(delim);
if (start == std::string_view::npos)
{
return iterator{ text, text.size(), text.size() };
}
auto end_word = text.find(delim, start);
if (end_word == std::string_view::npos)
{
end_word = text.size();
}
return iterator{ text, start, end_word };
}
[[nodiscard]] iterator end() const
{
return iterator{ text, text.size(), text.size() };
}
};
int main(int argc, char** argv)
{
using namespace std::literals;
auto str = " there should be no memory allocation during parsing"
" into words this line and you should'n create any"
" contaner for intermediate words "sv;
auto comma = "";
for (std::string_view word : split_by_spaces{ str })
{
std::cout << std::exchange(comma, ",") << std::quoted(word);
}
auto only_spaces = " "sv;
for (std::string_view word : split_by_spaces{ only_spaces })
{
std::cout << "you will not see this line in output" << std::endl;
}
}
