我在c++中使用以下方法解析字符串:

using namespace std;

string parsed,input="text to be parsed";
stringstream input_stringstream(input);

if (getline(input_stringstream,parsed,' '))
{
     // do some processing.
}

使用单个字符分隔符进行解析是可以的。但是如果我想使用字符串作为分隔符呢?

例子:我想拆分:

scott>=tiger

用>=作为分隔符,这样我就可以得到斯科特和老虎。


当前回答

由于这是c++分割字符串或类似的顶级Stack Overflow谷歌搜索结果,我将发布一个完整的、复制/粘贴可运行的示例,展示这两种方法。

splitString使用stringstream(在大多数情况下可能是更好更简单的选项)

splitString2使用find和substr(一种更手动的方法)

// SplitString.cpp

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

// function prototypes
std::vector<std::string> splitString(const std::string& str, char delim);
std::vector<std::string> splitString2(const std::string& str, char delim);
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx);


int main(void)
{
  // Test cases - all will pass
  
  std::string str = "ab,cd,ef";
  //std::string str = "abcdef";
  //std::string str = "";
  //std::string str = ",cd,ef";
  //std::string str = "ab,cd,";   // behavior of splitString and splitString2 is different for this final case only, if this case matters to you choose which one you need as applicable
  
  
  std::vector<std::string> tokens = splitString(str, ',');
  
  std::cout << "tokens: " << "\n";
  
  if (tokens.empty())
  {
    std::cout << "(tokens is empty)" << "\n";
  }
  else
  {
    for (auto& token : tokens)
    {
      if (token == "") std::cout << "(empty string)" << "\n";
      else std::cout << token << "\n";
    }
  }
    
  return 0;
}

std::vector<std::string> splitString(const std::string& str, char delim)
{
  std::vector<std::string> tokens;
  
  if (str == "") return tokens;
  
  std::string currentToken;
  
  std::stringstream ss(str);
  
  while (std::getline(ss, currentToken, delim))
  {
    tokens.push_back(currentToken);
  }
  
  return tokens;
}

std::vector<std::string> splitString2(const std::string& str, char delim)
{
  std::vector<std::string> tokens;
  
  if (str == "") return tokens;
  
  int leftIdx = 0;
  
  int delimIdx = str.find(delim);
  
  int rightIdx;
  
  while (delimIdx != std::string::npos)
  {
    rightIdx = delimIdx - 1;
    
    std::string token = getSubstring(str, leftIdx, rightIdx);
    tokens.push_back(token);
    
    // prep for next time around
    leftIdx = delimIdx + 1;
    
    delimIdx = str.find(delim, delimIdx + 1);
  }
  
  rightIdx = str.size() - 1;
  
  std::string token = getSubstring(str, leftIdx, rightIdx);
  tokens.push_back(token);
  
  return tokens;
}

std::string getSubstring(const std::string& str, int leftIdx, int rightIdx)
{
  return str.substr(leftIdx, rightIdx - leftIdx + 1);
}

其他回答

以下是我的看法。它处理边缘情况,并接受一个可选参数从结果中删除空条目。

bool endsWith(const std::string& s, const std::string& suffix)
{
    return s.size() >= suffix.size() &&
           s.substr(s.size() - suffix.size()) == suffix;
}

std::vector<std::string> split(const std::string& s, const std::string& delimiter, const bool removeEmptyEntries = false)
{
    std::vector<std::string> tokens;

    for (size_t start = 0, end; start < s.length(); start = end + delimiter.length())
    {
         size_t position = s.find(delimiter, start);
         end = position != std::string::npos ? position : s.length();

         std::string token = s.substr(start, end - start);
         if (!removeEmptyEntries || !token.empty())
         {
             tokens.push_back(token);
         }
    }

    if (!removeEmptyEntries &&
        (s.empty() || endsWith(s, delimiter)))
    {
        tokens.push_back("");
    }

    return tokens;
}

例子

split("a-b-c", "-"); // [3]("a","b","c")

split("a--c", "-"); // [3]("a","","c")

split("-b-", "-"); // [3]("","b","")

split("--c--", "-"); // [5]("","","c","","")

split("--c--", "-", true); // [1]("c")

split("a", "-"); // [1]("a")

split("", "-"); // [1]("")

split("", "-", true); // [0]()

你可以使用next函数拆分字符串:

vector<string> split(const string& str, const string& delim)
{
    vector<string> tokens;
    size_t prev = 0, pos = 0;
    do
    {
        pos = str.find(delim, prev);
        if (pos == string::npos) pos = str.length();
        string token = str.substr(prev, pos-prev);
        if (!token.empty()) tokens.push_back(token);
        prev = pos + delim.length();
    }
    while (pos < str.length() && prev < str.length());
    return tokens;
}

这是一个完整的方法,它在任何分隔符上分割字符串,并返回分割后的字符串的向量。

这是改编自ryanbwork的答案。然而,他的检查:if(token != mystring)给出错误的结果,如果你的字符串中有重复的元素。这是我对那个问题的解决方案。

vector<string> Split(string mystring, string delimiter)
{
    vector<string> subStringList;
    string token;
    while (true)
    {
        size_t findfirst = mystring.find_first_of(delimiter);
        if (findfirst == string::npos) //find_first_of returns npos if it couldn't find the delimiter anymore
        {
            subStringList.push_back(mystring); //push back the final piece of mystring
            return subStringList;
        }
        token = mystring.substr(0, mystring.find_first_of(delimiter));
        mystring = mystring.substr(mystring.find_first_of(delimiter) + 1);
        subStringList.push_back(token);
    }
    return subStringList;
}

用c++ 20实现的一种方法:

#include <iostream>
#include <ranges>
#include <string_view>

int main()
{
    std::string hello = "text to be parsed";
    auto split = hello
        | std::ranges::views::split(' ')
        | std::ranges::views::transform([](auto&& str) { return std::string_view(&*str.begin(), std::ranges::distance(str)); });

    for (auto&& word : split)
    {
        std::cout << word << std::endl;
    }
}

看到的: https://stackoverflow.com/a/48403210/10771848 https://en.cppreference.com/w/cpp/ranges/split_view

这个方法使用字符串find和字符串substr

vector<string> split(const string& str,const string delim){
vector<string> vtokens; 
size_t start = 0;
size_t end = 0;
while((end = str.find(delim,start))!=string::npos){
    vtokens.push_back(str.substr(start,end-start));
    start = end +1;
}
vtokens.push_back(str.substr(start));
return vtokens;
}