这里有一个仅使用标准正则表达式库的正则表达式解决方案。（我有点生疏，所以可能会有一些语法错误，但这至少是一般的想法）

#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
}

我相信还没有人发布这个解决方案。与其直接使用分隔符，它基本上与boost:：split（）相同，即它允许您传递一个谓词，如果字符是分隔符，则返回true，否则返回false。我认为这给了程序员更多的控制，最棒的是你不需要提升。

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;
    }
}

然后可以这样使用：

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;
    }
}

我对string和u32string~的一般实现，使用boost:：algorithm：：split签名。

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));
}

作为一个业余爱好者，这是我想到的第一个解决方案。我有点好奇，为什么我还没有在这里看到类似的解决方案，是不是我的做法有根本问题？

#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;
}

http://cpp.sh/7wmzy

我无法相信这些答案有多复杂。为什么没有人提出这么简单的建议？

#include <iostream>
#include <sstream>

std::string input = "This is a sentence to read";
std::istringstream ss(input);
std::string token;

while(std::getline(ss, token, ' ')) {
    std::cout << token << endl;
}

我喜欢将boost/regex方法用于此任务，因为它们为指定拆分条件提供了最大的灵活性。

#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;
}