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;
}

如果你愿意使用C语言，你可以使用strtok函数。在使用它时，您应该注意多线程问题。

If the maximum length of the input string to be tokenized is known, one can exploit this and implement a very fast version. I am sketching the basic idea below, which was inspired by both strtok() and the "suffix array"-data structure described Jon Bentley's "Programming Perls" 2nd edition, chapter 15. The C++ class in this case only gives some organization and convenience of use. The implementation shown can be easily extended for removing leading and trailing whitespace characters in the tokens.

基本上，可以将分隔符替换为以字符串结束的'\0'字符，并设置指向修改后字符串中的标记的指针。在极端情况下，当字符串仅由分隔符组成时，将得到字符串长度加1个空标记。复制要修改的字符串是可行的。

头文件:

class TextLineSplitter
{
public:

    TextLineSplitter( const size_t max_line_len );

    ~TextLineSplitter();

    void            SplitLine( const char *line,
                               const char sep_char = ',',
                             );

    inline size_t   NumTokens( void ) const
    {
        return mNumTokens;
    }

    const char *    GetToken( const size_t token_idx ) const
    {
        assert( token_idx < mNumTokens );
        return mTokens[ token_idx ];
    }

private:
    const size_t    mStorageSize;

    char           *mBuff;
    char          **mTokens;
    size_t          mNumTokens;

    inline void     ResetContent( void )
    {
        memset( mBuff, 0, mStorageSize );
        // mark all items as empty:
        memset( mTokens, 0, mStorageSize * sizeof( char* ) );
        // reset counter for found items:
        mNumTokens = 0L;
    }
};

Implementattion文件:

TextLineSplitter::TextLineSplitter( const size_t max_line_len ):
    mStorageSize ( max_line_len + 1L )
{
    // allocate memory
    mBuff   = new char  [ mStorageSize ];
    mTokens = new char* [ mStorageSize ];

    ResetContent();
}

TextLineSplitter::~TextLineSplitter()
{
    delete [] mBuff;
    delete [] mTokens;
}


void TextLineSplitter::SplitLine( const char *line,
                                  const char sep_char   /* = ',' */,
                                )
{
    assert( sep_char != '\0' );

    ResetContent();
    strncpy( mBuff, line, mMaxLineLen );

    size_t idx       = 0L; // running index for characters

    do
    {
        assert( idx < mStorageSize );

        const char chr = line[ idx ]; // retrieve current character

        if( mTokens[ mNumTokens ] == NULL )
        {
            mTokens[ mNumTokens ] = &mBuff[ idx ];
        } // if

        if( chr == sep_char || chr == '\0' )
        { // item or line finished
            // overwrite separator with a 0-terminating character:
            mBuff[ idx ] = '\0';
            // count-up items:
            mNumTokens ++;
        } // if

    } while( line[ idx++ ] );
}

使用的场景是:

// create an instance capable of splitting strings up to 1000 chars long:
TextLineSplitter spl( 1000 );
spl.SplitLine( "Item1,,Item2,Item3" );
for( size_t i = 0; i < spl.NumTokens(); i++ )
{
    printf( "%s\n", spl.GetToken( i ) );
}

输出:

Item1

Item2
Item3

pystring是一个小型库，实现了Python的一系列字符串函数，包括split方法:

#include <string>
#include <vector>
#include "pystring.h"

std::vector<std::string> chunks;
pystring::split("this string", chunks);

// also can specify a separator
pystring::split("this-string", chunks, "-");

下面是一个示例标记器类，它可以实现您想要的功能

//Header file
class Tokenizer 
{
    public:
        static const std::string DELIMITERS;
        Tokenizer(const std::string& str);
        Tokenizer(const std::string& str, const std::string& delimiters);
        bool NextToken();
        bool NextToken(const std::string& delimiters);
        const std::string GetToken() const;
        void Reset();
    protected:
        size_t m_offset;
        const std::string m_string;
        std::string m_token;
        std::string m_delimiters;
};

//CPP file
const std::string Tokenizer::DELIMITERS(" \t\n\r");

Tokenizer::Tokenizer(const std::string& s) :
    m_string(s), 
    m_offset(0), 
    m_delimiters(DELIMITERS) {}

Tokenizer::Tokenizer(const std::string& s, const std::string& delimiters) :
    m_string(s), 
    m_offset(0), 
    m_delimiters(delimiters) {}

bool Tokenizer::NextToken() 
{
    return NextToken(m_delimiters);
}

bool Tokenizer::NextToken(const std::string& delimiters) 
{
    size_t i = m_string.find_first_not_of(delimiters, m_offset);
    if (std::string::npos == i) 
    {
        m_offset = m_string.length();
        return false;
    }

    size_t j = m_string.find_first_of(delimiters, i);
    if (std::string::npos == j) 
    {
        m_token = m_string.substr(i);
        m_offset = m_string.length();
        return true;
    }

    m_token = m_string.substr(i, j - i);
    m_offset = j;
    return true;
}

例子:

std::vector <std::string> v;
Tokenizer s("split this string", " ");
while (s.NextToken())
{
    v.push_back(s.GetToken());
}

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;
}