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;
}

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;
}

请看这个例子。它可能对你有帮助。

#include <iostream>
#include <sstream>

using namespace std;

int main ()
{
    string tmps;
    istringstream is ("the dellimiter is the space");
    while (is.good ()) {
        is >> tmps;
        cout << tmps << "\n";
    }
    return 0;
}

使用regex_token_iterators的解决方案:

#include <iostream>
#include <regex>
#include <string>

using namespace std;

int main()
{
    string str("The quick brown fox");

    regex reg("\\s+");

    sregex_token_iterator iter(str.begin(), str.end(), reg, -1);
    sregex_token_iterator end;

    vector<string> vec(iter, end);

    for (auto a : vec)
    {
        cout << a << endl;
    }
}

这是一个简单的stl解决方案(~5行!)使用std::find和std::find_first_not_of来处理重复的分隔符(例如空格或句号)，以及开头和结尾的分隔符:

#include <string>
#include <vector>

void tokenize(std::string str, std::vector<string> &token_v){
    size_t start = str.find_first_not_of(DELIMITER), end=start;

    while (start != std::string::npos){
        // Find next occurence of delimiter
        end = str.find(DELIMITER, start);
        // Push back the token found into vector
        token_v.push_back(str.substr(start, end-start));
        // Skip all occurences of the delimiter to find new start
        start = str.find_first_not_of(DELIMITER, end);
    }
}

现场试试吧!

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;
}