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

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!

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;
    }
}

下面是一种方法，允许您控制是否包含空标记(如strsep)或排除空标记(如strtok)。

#include <string.h> // for strchr and strlen

/*
 * want_empty_tokens==true  : include empty tokens, like strsep()
 * want_empty_tokens==false : exclude empty tokens, like strtok()
 */
std::vector<std::string> tokenize(const char* src,
                                  char delim,
                                  bool want_empty_tokens)
{
  std::vector<std::string> tokens;

  if (src and *src != '\0') // defensive
    while( true )  {
      const char* d = strchr(src, delim);
      size_t len = (d)? d-src : strlen(src);

      if (len or want_empty_tokens)
        tokens.push_back( std::string(src, len) ); // capture token

      if (d) src += len+1; else break;
    }

  return tokens;
}

我为自己编写了一个https://stackoverflow.com/a/50247503/3976739的简化版本(可能有一点效率)。我希望这能有所帮助。

void StrTokenizer(string& source, const char* delimiter, vector<string>& Tokens)
{   
   size_t new_index = 0;
   size_t old_index = 0;

   while (new_index != std::string::npos)   
   {
      new_index = source.find(delimiter, old_index);
      Tokens.emplace_back(source.substr(old_index, new_index-old_index));

      if (new_index != std::string::npos)
          old_index = ++new_index;
   }
}

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;
}