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

无意冒犯，但对于这样一个简单的问题，你把事情搞得太复杂了。使用Boost有很多理由。但对于这么简单的事情，就像用20号雪橇打苍蝇一样。

void
split( vector<string> & theStringVector,  /* Altered/returned value */
       const  string  & theString,
       const  string  & theDelimiter)
{
    UASSERT( theDelimiter.size(), >, 0); // My own ASSERT macro.

    size_t  start = 0, end = 0;

    while ( end != string::npos)
    {
        end = theString.find( theDelimiter, start);

        // If at end, use length=maxLength.  Else use length=end-start.
        theStringVector.push_back( theString.substr( start,
                       (end == string::npos) ? string::npos : end - start));

        // If at end, use start=maxSize.  Else use start=end+delimiter.
        start = (   ( end > (string::npos - theDelimiter.size()) )
                  ?  string::npos  :  end + theDelimiter.size());
    }
}

例如(以Doug为例)，

#define SHOW(I,X)   cout << "[" << (I) << "]\t " # X " = \"" << (X) << "\"" << endl

int
main()
{
    vector<string> v;

    split( v, "A:PEP:909:Inventory Item", ":" );

    for (unsigned int i = 0;  i < v.size();   i++)
        SHOW( i, v[i] );
}

是的，我们可以split()返回一个新的向量，而不是传入一个。包装和重载是很简单的。但根据我所做的事情，我经常发现重用已有的对象比总是创建新对象更好。(只要我不忘记清空中间的向量!)

参考:http://www.cplusplus.com/reference/string/string/。

(我最初是在写一个回应Doug的问题:基于分隔符的c++字符串修改和提取(关闭)。但由于马丁·约克用这里的指针结束了这个问题……我将泛化我的代码。)

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!

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;
}

我知道这个问题已经有了答案，但我想有所贡献。也许我的解决方案有点简单，但这就是我想到的:

vector<string> get_words(string const& text, string const& separator)
{
    vector<string> result;
    string tmp = text;

    size_t first_pos = 0;
    size_t second_pos = tmp.find(separator);

    while (second_pos != string::npos)
    {
        if (first_pos != second_pos)
        {
            string word = tmp.substr(first_pos, second_pos - first_pos);
            result.push_back(word);
        }
        tmp = tmp.substr(second_pos + separator.length());
        second_pos = tmp.find(separator);
    }

    result.push_back(tmp);

    return result;
}

如果在我的代码中有更好的方法，或者有什么错误，请评论。

更新:添加通用分隔符

另一种快速方法是使用getline。喜欢的东西:

stringstream ss("bla bla");
string s;

while (getline(ss, s, ' ')) {
 cout << s << endl;
}

如果需要，可以创建一个简单的split()方法，返回vector<string>，即 真的有用。