下面是我的Swiss®军刀字符串标记器，用于用空格分隔字符串，处理单引号和双引号包装的字符串，以及从结果中剥离这些字符。我使用RegexBuddy 4。x生成大部分代码片段，但我添加了用于剥离引号和其他一些东西的自定义处理。

#include <string>
#include <locale>
#include <regex>

std::vector<std::wstring> tokenize_string(std::wstring string_to_tokenize) {
    std::vector<std::wstring> tokens;

    std::wregex re(LR"(("[^"]*"|'[^']*'|[^"' ]+))", std::regex_constants::collate);

    std::wsregex_iterator next( string_to_tokenize.begin(),
                                string_to_tokenize.end(),
                                re,
                                std::regex_constants::match_not_null );

    std::wsregex_iterator end;
    const wchar_t single_quote = L'\'';
    const wchar_t double_quote = L'\"';
    while ( next != end ) {
        std::wsmatch match = *next;
        const std::wstring token = match.str( 0 );
        next++;

        if (token.length() > 2 && (token.front() == double_quote || token.front() == single_quote))
            tokens.emplace_back( std::wstring(token.begin()+1, token.begin()+token.length()-1) );
        else
            tokens.emplace_back(token);
    }
    return tokens;
}

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;
}

Adam Pierce的回答提供了一个采用const char*的手工标记器。使用迭代器会有一些问题，因为对字符串的结束迭代器进行递增是未定义的。也就是说，给定字符串str{"The quick brown fox"}，我们当然可以做到:

auto start = find(cbegin(str), cend(str), ' ');
vector<string> tokens{ string(cbegin(str), start) };

while (start != cend(str)) {
    const auto finish = find(++start, cend(str), ' ');

    tokens.push_back(string(start, finish));
    start = finish;
}

生活的例子

如果你想通过使用标准功能来抽象复杂性，On Freund建议strtok是一个简单的选择:

vector<string> tokens;

for (auto i = strtok(data(str), " "); i != nullptr; i = strtok(nullptr, " ")) tokens.push_back(i);

如果你不能访问c++ 17，你需要像这个例子一样替换data(str): http://ideone.com/8kAGoa

虽然在示例中没有演示，但strtok不需要为每个标记使用相同的分隔符。除了这个优势，还有几个缺点:

strtok cannot be used on multiple strings at the same time: Either a nullptr must be passed to continue tokenizing the current string or a new char* to tokenize must be passed (there are some non-standard implementations which do support this however, such as: strtok_s) For the same reason strtok cannot be used on multiple threads simultaneously (this may however be implementation defined, for example: Visual Studio's implementation is thread safe) Calling strtok modifies the string it is operating on, so it cannot be used on const strings, const char*s, or literal strings, to tokenize any of these with strtok or to operate on a string who's contents need to be preserved, str would have to be copied, then the copy could be operated on

c++20为我们提供了split_view来以非破坏性的方式标记字符串:https://topanswers.xyz/cplusplus?q=749#a874

前面的方法不能就地生成标记化的向量，这意味着如果不将它们抽象为辅助函数，它们就不能初始化const vector<string>令牌。该功能和接受任何空白分隔符的能力可以使用istream_iterator来利用。例如，给定const string str{"The quick \tbrown \nfox"}，我们可以这样做:

istringstream is{ str };
const vector<string> tokens{ istream_iterator<string>(is), istream_iterator<string>() };

生活的例子

对于这个选项，需要构造一个istringstream的代价比前面两个选项要大得多，但是这个代价通常隐藏在字符串分配的代价中。

如果上面的选项都不够灵活，不能满足您的标记化需求，那么最灵活的选项是使用regex_token_iterator，当然这种灵活性会带来更大的开销，但同样，这可能隐藏在字符串分配成本中。例如，我们想要基于非转义的逗号进行标记化，也吃空白，给定以下输入:const string str{" the,qu\\，ick，\tbrown, fox"}我们可以这样做:

const regex re{ "\\s*((?:[^\\\\,]|\\\\.)*?)\\s*(?:,|$)" };
const vector<string> tokens{ sregex_token_iterator(cbegin(str), cend(str), re, 1), sregex_token_iterator() };

生活的例子

在我看来很奇怪的是，SO网站上有这么多注重速度的书呆子，却没有人给出一个使用编译时生成的分隔符查找表的版本(下面是示例实现)。使用查找表和迭代器应该在效率上击败std::regex，如果你不需要击败regex，就使用它，它是c++ 11的标准，超级灵活。

有些人已经建议使用正则表达式，但对于新手来说，这里有一个打包的示例，应该完全符合OP的期望:

std::vector<std::string> split(std::string::const_iterator it, std::string::const_iterator end, std::regex e = std::regex{"\\w+"}){
    std::smatch m{};
    std::vector<std::string> ret{};
    while (std::regex_search (it,end,m,e)) {
        ret.emplace_back(m.str());              
        std::advance(it, m.position() + m.length()); //next start position = match position + match length
    }
    return ret;
}
std::vector<std::string> split(const std::string &s, std::regex e = std::regex{"\\w+"}){  //comfort version calls flexible version
    return split(s.cbegin(), s.cend(), std::move(e));
}
int main ()
{
    std::string str {"Some people, excluding those present, have been compile time constants - since puberty."};
    auto v = split(str);
    for(const auto&s:v){
        std::cout << s << std::endl;
    }
    std::cout << "crazy version:" << std::endl;
    v = split(str, std::regex{"[^e]+"});  //using e as delim shows flexibility
    for(const auto&s:v){
        std::cout << s << std::endl;
    }
    return 0;
}

如果我们需要更快并接受所有字符必须为8位的约束，我们可以在编译时使用元编程创建一个查找表:

template<bool...> struct BoolSequence{};        //just here to hold bools
template<char...> struct CharSequence{};        //just here to hold chars
template<typename T, char C> struct Contains;   //generic
template<char First, char... Cs, char Match>    //not first specialization
struct Contains<CharSequence<First, Cs...>,Match> :
    Contains<CharSequence<Cs...>, Match>{};     //strip first and increase index
template<char First, char... Cs>                //is first specialization
struct Contains<CharSequence<First, Cs...>,First>: std::true_type {}; 
template<char Match>                            //not found specialization
struct Contains<CharSequence<>,Match>: std::false_type{};

template<int I, typename T, typename U> 
struct MakeSequence;                            //generic
template<int I, bool... Bs, typename U> 
struct MakeSequence<I,BoolSequence<Bs...>, U>:  //not last
    MakeSequence<I-1, BoolSequence<Contains<U,I-1>::value,Bs...>, U>{};
template<bool... Bs, typename U> 
struct MakeSequence<0,BoolSequence<Bs...>,U>{   //last  
    using Type = BoolSequence<Bs...>;
};
template<typename T> struct BoolASCIITable;
template<bool... Bs> struct BoolASCIITable<BoolSequence<Bs...>>{
    /* could be made constexpr but not yet supported by MSVC */
    static bool isDelim(const char c){
        static const bool table[256] = {Bs...};
        return table[static_cast<int>(c)];
    }   
};
using Delims = CharSequence<'.',',',' ',':','\n'>;  //list your custom delimiters here
using Table = BoolASCIITable<typename MakeSequence<256,BoolSequence<>,Delims>::Type>;

有了这些，创建getNextToken函数就很容易了:

template<typename T_It>
std::pair<T_It,T_It> getNextToken(T_It begin,T_It end){
    begin = std::find_if(begin,end,std::not1(Table{})); //find first non delim or end
    auto second = std::find_if(begin,end,Table{});      //find first delim or end
    return std::make_pair(begin,second);
}

使用它也很简单:

int main() {
    std::string s{"Some people, excluding those present, have been compile time constants - since puberty."};
    auto it = std::begin(s);
    auto end = std::end(s);
    while(it != std::end(s)){
        auto token = getNextToken(it,end);
        std::cout << std::string(token.first,token.second) << std::endl;
        it = token.second;
    }
    return 0;
}

这里有一个生动的例子:http://ideone.com/GKtkLQ

下面是我的Swiss®军刀字符串标记器，用于用空格分隔字符串，处理单引号和双引号包装的字符串，以及从结果中剥离这些字符。我使用RegexBuddy 4。x生成大部分代码片段，但我添加了用于剥离引号和其他一些东西的自定义处理。

#include <string>
#include <locale>
#include <regex>

std::vector<std::wstring> tokenize_string(std::wstring string_to_tokenize) {
    std::vector<std::wstring> tokens;

    std::wregex re(LR"(("[^"]*"|'[^']*'|[^"' ]+))", std::regex_constants::collate);

    std::wsregex_iterator next( string_to_tokenize.begin(),
                                string_to_tokenize.end(),
                                re,
                                std::regex_constants::match_not_null );

    std::wsregex_iterator end;
    const wchar_t single_quote = L'\'';
    const wchar_t double_quote = L'\"';
    while ( next != end ) {
        std::wsmatch match = *next;
        const std::wstring token = match.str( 0 );
        next++;

        if (token.length() > 2 && (token.front() == double_quote || token.front() == single_quote))
            tokens.emplace_back( std::wstring(token.begin()+1, token.begin()+token.length()-1) );
        else
            tokens.emplace_back(token);
    }
    return tokens;
}

我以前只用标准库做了一个lexer/tokenizer。代码如下:

#include <iostream>
#include <string>
#include <vector>
#include <sstream>

using namespace std;

string seps(string& s) {
    if (!s.size()) return "";
    stringstream ss;
    ss << s[0];
    for (int i = 1; i < s.size(); i++) {
        ss << '|' << s[i];
    }
    return ss.str();
}

void Tokenize(string& str, vector<string>& tokens, const string& delimiters = " ")
{
    seps(str);

    // 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);
    }
}

int main(int argc, char *argv[])
{
    vector<string> t;
    string s = "Tokens for everyone!";

    Tokenize(s, t, "|");

    for (auto c : t)
        cout << c << endl;

    system("pause");

    return 0;
}