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

最小的解决方案是一个函数,它将std::字符串和一组分隔符(作为std::string)作为输入,并返回std:::字符串的std::向量。

#include <string>
#include <vector>

std::vector<std::string>
tokenize(const std::string& str, const std::string& delimiters)
{
  using ssize_t = std::string::size_type;
  const ssize_t str_ln = str.length();
  ssize_t last_pos = 0;

  // container for the extracted tokens
  std::vector<std::string> tokens;

  while (last_pos < str_ln) {
      // find the position of the next delimiter
      ssize_t pos = str.find_first_of(delimiters, last_pos);

      // if no delimiters found, set the position to the length of string
      if (pos == std::string::npos)
         pos = str_ln;

      // if the substring is nonempty, store it in the container
      if (pos != last_pos)
         tokens.emplace_back(str.substr(last_pos, pos - last_pos));

      // scan past the previous substring
      last_pos = pos + 1;
  }

  return tokens;
}

用法示例:

#include <iostream>

int main()
{
    std::string input_str = "one + two * (three - four)!!---! ";
    const char* delimiters = "! +- (*)";
    std::vector<std::string> tokens = tokenize(input_str, delimiters);

    std::cout << "input = '" << input_str << "'\n"
              << "delimiters = '" << delimiters << "'\n"
              << "nr of tokens found = " << tokens.size() << std::endl;
    for (const std::string& tk : tokens) {
        std::cout << "token = '" << tk << "'\n";
    }

  return 0;
}

其他回答

使用Boost的可能解决方案可能是:

#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));

这种方法可能比字符串流方法更快。由于这是一个通用模板函数,因此可以使用各种分隔符拆分其他类型的字符串(wchar等或UTF-8)。

有关详细信息,请参阅文档。

我喜欢下面的代码,因为它将结果放入一个向量中,支持字符串作为delim,并控制保持空值。但是,那时候看起来不太好。

#include <ostream>
#include <string>
#include <vector>
#include <algorithm>
#include <iterator>
using namespace std;

vector<string> split(const string& s, const string& delim, const bool keep_empty = true) {
    vector<string> result;
    if (delim.empty()) {
        result.push_back(s);
        return result;
    }
    string::const_iterator substart = s.begin(), subend;
    while (true) {
        subend = search(substart, s.end(), delim.begin(), delim.end());
        string temp(substart, subend);
        if (keep_empty || !temp.empty()) {
            result.push_back(temp);
        }
        if (subend == s.end()) {
            break;
        }
        substart = subend + delim.size();
    }
    return result;
}

int main() {
    const vector<string> words = split("So close no matter how far", " ");
    copy(words.begin(), words.end(), ostream_iterator<string>(cout, "\n"));
}

当然,Boost有一个split(),它的部分功能与此类似。而且,如果“空白”是指任何类型的空白,那么使用Boost的split和is_any_of()都非常有用。

我的代码是:

#include <list>
#include <string>
template<class StringType = std::string, class ContainerType = std::list<StringType> >
class DSplitString:public ContainerType
{
public:
    explicit DSplitString(const StringType& strString, char cChar, bool bSkipEmptyParts = true)
    {
        size_t iPos = 0;
        size_t iPos_char = 0;
        while(StringType::npos != (iPos_char = strString.find(cChar, iPos)))
        {
            StringType strTemp = strString.substr(iPos, iPos_char - iPos);
            if((bSkipEmptyParts && !strTemp.empty()) || (!bSkipEmptyParts))
                push_back(strTemp);
            iPos = iPos_char + 1;
        }
    }
    explicit DSplitString(const StringType& strString, const StringType& strSub, bool bSkipEmptyParts = true)
    {
        size_t iPos = 0;
        size_t iPos_char = 0;
        while(StringType::npos != (iPos_char = strString.find(strSub, iPos)))
        {
            StringType strTemp = strString.substr(iPos, iPos_char - iPos);
            if((bSkipEmptyParts && !strTemp.empty()) || (!bSkipEmptyParts))
                push_back(strTemp);
            iPos = iPos_char + strSub.length();
        }
    }
};

例子:

#include <iostream>
#include <string>
int _tmain(int argc, _TCHAR* argv[])
{
    DSplitString<> aa("doicanhden1;doicanhden2;doicanhden3;", ';');
    for each (std::string var in aa)
    {
        std::cout << var << std::endl;
    }
    std::cin.get();
    return 0;
}

使用vector作为基类的快速版本,可完全访问其所有运算符:

    // Split string into parts.
    class Split : public std::vector<std::string>
    {
        public:
            Split(const std::string& str, char* delimList)
            {
               size_t lastPos = 0;
               size_t pos = str.find_first_of(delimList);

               while (pos != std::string::npos)
               {
                    if (pos != lastPos)
                        push_back(str.substr(lastPos, pos-lastPos));
                    lastPos = pos + 1;
                    pos = str.find_first_of(delimList, lastPos);
               }
               if (lastPos < str.length())
                   push_back(str.substr(lastPos, pos-lastPos));
            }
    };

用于填充STL集的示例:

std::set<std::string> words;
Split split("Hello,World", ",");
words.insert(split.begin(), split.end());

这类似于堆栈溢出问题:如何在C++中标记字符串?。需要Boost外部库

#include <iostream>
#include <string>
#include <boost/tokenizer.hpp>

using namespace std;
using namespace boost;

int main(int argc, char** argv)
{
    string text = "token  test\tstring";

    char_separator<char> sep(" \t");
    tokenizer<char_separator<char>> tokens(text, sep);
    for (const string& t : tokens)
    {
        cout << t << "." << endl;
    }
}