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

下面是一个更好的方法。它可以接受任何字符,除非您愿意,否则不会拆分行。不需要特殊的库(嗯,除了std,但谁真的认为这是一个额外的库),没有指针,没有引用,而且它是静态的。只是简单的C++。

#pragma once
#include <vector>
#include <sstream>
using namespace std;
class Helpers
{
    public:
        static vector<string> split(string s, char delim)
        {
            stringstream temp (stringstream::in | stringstream::out);
            vector<string> elems(0);
            if (s.size() == 0 || delim == 0)
                return elems;
            for(char c : s)
            {
                if(c == delim)
                {
                    elems.push_back(temp.str());
                    temp = stringstream(stringstream::in | stringstream::out);
                }
                else
                    temp << c;
            }
            if (temp.str().size() > 0)
                elems.push_back(temp.str());
                return elems;
            }

        //Splits string s with a list of delimiters in delims (it's just a list, like if we wanted to
        //split at the following letters, a, b, c we would make delims="abc".
        static vector<string> split(string s, string delims)
        {
            stringstream temp (stringstream::in | stringstream::out);
            vector<string> elems(0);
            bool found;
            if(s.size() == 0 || delims.size() == 0)
                return elems;
            for(char c : s)
            {
                found = false;
                for(char d : delims)
                {
                    if (c == d)
                    {
                        elems.push_back(temp.str());
                        temp = stringstream(stringstream::in | stringstream::out);
                        found = true;
                        break;
                    }
                }
                if(!found)
                    temp << c;
            }
            if(temp.str().size() > 0)
                elems.push_back(temp.str());
            return elems;
        }
};

其他回答

仅为方便:

template<class V, typename T>
bool in(const V &v, const T &el) {
    return std::find(v.begin(), v.end(), el) != v.end();
}

基于多个分隔符的实际拆分:

std::vector<std::string> split(const std::string &s,
                               const std::vector<char> &delims) {
    std::vector<std::string> res;
    auto stuff = [&delims](char c) { return !in(delims, c); };
    auto space = [&delims](char c) { return in(delims, c); };
    auto first = std::find_if(s.begin(), s.end(), stuff);
    while (first != s.end()) {
        auto last = std::find_if(first, s.end(), space);
        res.push_back(std::string(first, last));
        first = std::find_if(last + 1, s.end(), stuff);
    }
    return res;
}

用法:

int main() {
    std::string s = "   aaa,  bb  cc ";
    for (auto el: split(s, {' ', ','}))
        std::cout << el << std::endl;
    return 0;
}

STL还没有这样的方法。

但是,您可以通过使用std::string::C_str()成员来使用C的strtok()函数,也可以编写自己的函数。下面是我在快速谷歌搜索(“STL字符串分割”)后找到的代码示例:

void Tokenize(const string& str,
              vector<string>& tokens,
              const string& delimiters = " ")
{
    // 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);
    }
}

摘自:http://oopweb.com/CPP/Documents/CPPHOWTO/Volume/C++编程-HOWTO-7.html

如果您对代码示例有疑问,请留下评论,我会解释。

仅仅因为它没有实现称为迭代器的typedef或重载<<运算符,并不意味着它是错误的代码。我经常使用C函数。例如,printf和scanf都比std::cin和std::cout快(很明显),fopen语法对二进制类型更友好,它们也倾向于生成更小的EXE。

不要被这种“优雅胜过性能”的交易所吸引。

这个呢

#include <string>
#include <vector>

using namespace std;

vector<string> split(string str, const char delim) {
    vector<string> v;
    string tmp;

    for(string::const_iterator i; i = str.begin(); i <= str.end(); ++i) {
        if(*i != delim && i != str.end()) {
            tmp += *i; 
        } else {
            v.push_back(tmp);
            tmp = ""; 
        }   
    }   

    return v;
}

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;)

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;
}