如何迭代由空格分隔的单词组成的字符串中的单词?

注意,我对C字符串函数或那种字符操作/访问不感兴趣。比起效率,我更喜欢优雅。我当前的解决方案:

#include <iostream>
#include <sstream>
#include <string>

using namespace std;

int main() {
    string s = "Somewhere down the road";
    istringstream iss(s);

    do {
        string subs;
        iss >> subs;
        cout << "Substring: " << subs << endl;
    } while (iss);
}

当前回答

这里有一个只使用标准正则表达式库的简单解决方案

#include <regex>
#include <string>
#include <vector>

std::vector<string> Tokenize( const string str, const std::regex regex )
{
    using namespace std;

    std::vector<string> result;

    sregex_token_iterator it( str.begin(), str.end(), regex, -1 );
    sregex_token_iterator reg_end;

    for ( ; it != reg_end; ++it ) {
        if ( !it->str().empty() ) //token could be empty:check
            result.emplace_back( it->str() );
    }

    return result;
}

正则表达式参数允许检查多个参数(空格、逗号等)

我通常只选中空格和逗号分隔,所以我也有这个默认函数:

std::vector<string> TokenizeDefault( const string str )
{
    using namespace std;

    regex re( "[\\s,]+" );

    return Tokenize( str, re );
}

“[\\s,]+”检查空格(\\s)和逗号(,)。

注意,如果要拆分wstring而不是string,

将所有std::regex更改为std::wregex将所有sregex_token_iterator更改为wsregex_token_idterator

注意,根据编译器的不同,您可能还希望引用字符串参数。

其他回答

另一种灵活快速的方式

template<typename Operator>
void tokenize(Operator& op, const char* input, const char* delimiters) {
  const char* s = input;
  const char* e = s;
  while (*e != 0) {
    e = s;
    while (*e != 0 && strchr(delimiters, *e) == 0) ++e;
    if (e - s > 0) {
      op(s, e - s);
    }
    s = e + 1;
  }
}

要将其与字符串向量一起使用(编辑:由于有人指出不继承STL类…hrmf;):

template<class ContainerType>
class Appender {
public:
  Appender(ContainerType& container) : container_(container) {;}
  void operator() (const char* s, unsigned length) { 
    container_.push_back(std::string(s,length));
  }
private:
  ContainerType& container_;
};

std::vector<std::string> strVector;
Appender v(strVector);
tokenize(v, "A number of words to be tokenized", " \t");

就是这样!这只是使用tokenizer的一种方式,比如如何计数单词:

class WordCounter {
public:
  WordCounter() : noOfWords(0) {}
  void operator() (const char*, unsigned) {
    ++noOfWords;
  }
  unsigned noOfWords;
};

WordCounter wc;
tokenize(wc, "A number of words to be counted", " \t"); 
ASSERT( wc.noOfWords == 7 );

受限于想象力;)

我已经使用strtok滚动了自己的代码,并使用boost拆分了一个字符串。我找到的最好的方法是C++字符串工具包库。它非常灵活和快速。

#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;
}

该工具包比这个简单示例显示的灵活性要高得多,但它在将字符串解析为有用元素方面的实用性令人难以置信。

#include<iostream>
#include<string>
#include<sstream>
#include<vector>
using namespace std;

    vector<string> split(const string &s, char delim) {
        vector<string> elems;
        stringstream ss(s);
        string item;
        while (getline(ss, item, delim)) {
            elems.push_back(item);
        }
        return elems;
    }

int main() {

        vector<string> x = split("thi is an sample test",' ');
        unsigned int i;
        for(i=0;i<x.size();i++)
            cout<<i<<":"<<x[i]<<endl;
        return 0;
}

并不是说我们需要更多的答案,但这是我受到埃文·特兰启发后想到的。

std::vector <std::string> split(const string &input, auto delimiter, bool skipEmpty=true) {
  /*
  Splits a string at each delimiter and returns these strings as a string vector.
  If the delimiter is not found then nothing is returned.
  If skipEmpty is true then strings between delimiters that are 0 in length will be skipped.
  */
  bool delimiterFound = false;
  int pos=0, pPos=0;
  std::vector <std::string> result;
  while (true) {
    pos = input.find(delimiter,pPos);
    if (pos != std::string::npos) {
      if (skipEmpty==false or pos-pPos > 0) // if empty values are to be kept or not
        result.push_back(input.substr(pPos,pos-pPos));
      delimiterFound = true;
    } else {
      if (pPos < input.length() and delimiterFound) {
        if (skipEmpty==false or input.length()-pPos > 0) // if empty values are to be kept or not
          result.push_back(input.substr(pPos,input.length()-pPos));
      }
      break;
    }
    pPos = pos+1;
  }
  return result;
}

这是我使用C++11和STL的解决方案。它应该是合理有效的:

#include <vector>
#include <string>
#include <cstring>
#include <iostream>
#include <algorithm>
#include <functional>

std::vector<std::string> split(const std::string& s)
{
    std::vector<std::string> v;

    const auto end = s.end();
    auto to = s.begin();
    decltype(to) from;

    while((from = std::find_if(to, end,
        [](char c){ return !std::isspace(c); })) != end)
    {
        to = std::find_if(from, end, [](char c){ return std::isspace(c); });
        v.emplace_back(from, to);
    }

    return v;
}

int main()
{
    std::string s = "this is the string  to  split";

    auto v = split(s);

    for(auto&& s: v)
        std::cout << s << '\n';
}

输出:

this
is
the
string
to
split