Java有一个方便的分割方法:

String str = "The quick brown fox";
String[] results = str.split(" ");

在c++中有简单的方法来做到这一点吗?


当前回答

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

其他回答

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

我贴出了类似问题的答案。 不要白费力气。我使用过许多库,我遇到过的最快、最灵活的库是:c++ String Toolkit Library。

这里有一个如何使用它的例子,我已经张贴在stackoverflow的其他地方。

#include <iostream>
#include <vector>
#include <string>
#include <strtk.hpp>

const char *whitespace  = " \t\r\n\f";
const char *whitespace_and_punctuation  = " \t\r\n\f;,=";

int main()
{
    {   // normal parsing of a string into a vector of strings
       std::string s("Somewhere down the road");
       std::vector<std::string> result;
       if( strtk::parse( s, whitespace, result ) )
       {
           for(size_t i = 0; i < result.size(); ++i )
            std::cout << result[i] << std::endl;
       }
    }

    {  // parsing a string into a vector of floats with other separators
       // besides spaces

       std::string s("3.0, 3.14; 4.0");
       std::vector<float> values;
       if( strtk::parse( s, whitespace_and_punctuation, values ) )
       {
           for(size_t i = 0; i < values.size(); ++i )
            std::cout << values[i] << std::endl;
       }
    }

    {  // parsing a string into specific variables

       std::string s("angle = 45; radius = 9.9");
       std::string w1, w2;
       float v1, v2;
       if( strtk::parse( s, whitespace_and_punctuation, w1, v1, w2, v2) )
       {
           std::cout << "word " << w1 << ", value " << v1 << std::endl;
           std::cout << "word " << w2 << ", value " << v2 << std::endl;
       }
    }

    return 0;
}

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

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;
    }
}

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;
}