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

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

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]()

我会使用boost::tokenizer。下面的文档解释了如何创建适当的标记器函数:http://www.boost.org/doc/libs/1_52_0/libs/tokenizer/tokenizerfunction.htm

这里有一个对你的案子有用。

struct my_tokenizer_func
{
    template<typename It>
    bool operator()(It& next, It end, std::string & tok)
    {
        if (next == end)
            return false;
        char const * del = ">=";
        auto pos = std::search(next, end, del, del + 2);
        tok.assign(next, pos);
        next = pos;
        if (next != end)
            std::advance(next, 2);
        return true;
    }

    void reset() {}
};

int main()
{
    std::string to_be_parsed = "1) one>=2) two>=3) three>=4) four";
    for (auto i : boost::tokenizer<my_tokenizer_func>(to_be_parsed))
        std::cout << i << '\n';
}

对于字符串(或单个字符)分隔符,这应该非常有效。不要忘记包含#include <sstream>。

std::string input = "Alfa=,+Bravo=,+Charlie=,+Delta";
std::string delimiter = "=,+"; 
std::istringstream ss(input);
std::string token;
std::string::iterator it;

while(std::getline(ss, token, *(it = delimiter.begin()))) {
    std::cout << token << std::endl; // Token is extracted using '='
    it++;
    // Skip the rest of delimiter if exists ",+"
    while(it != delimiter.end() and ss.peek() == *(it)) { 
        it++; ss.get(); 
    }
}

第一个while循环使用字符串分隔符的第一个字符提取一个标记。第二个while循环跳过分隔符的其余部分,停在下一个标记的开头。

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);
}

对于字符串分隔符

基于字符串分隔符拆分字符串。如分割字符串“adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih”基于字符串分隔符“-+”,输出将是{“adsf”,“qwret”,“nvfkbdsj”,“orthdfjgh”,“dfjrleih”}

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

using namespace std;

// for string delimiter
vector<string> split (string s, string delimiter) {
    size_t pos_start = 0, pos_end, delim_len = delimiter.length();
    string token;
    vector<string> res;

    while ((pos_end = s.find (delimiter, pos_start)) != string::npos) {
        token = s.substr (pos_start, pos_end - pos_start);
        pos_start = pos_end + delim_len;
        res.push_back (token);
    }

    res.push_back (s.substr (pos_start));
    return res;
}

int main() {
    string str = "adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih";
    string delimiter = "-+";
    vector<string> v = split (str, delimiter);

    for (auto i : v) cout << i << endl;

    return 0;
}

**Output**
adsf
qwret
nvfkbdsj
orthdfjgh
dfjrleih

对于单字符分隔符

基于字符分隔符拆分字符串。例如,使用分隔符“+”分割字符串“adsf+qwer+poui+fdgh”将输出{“adsf”,“qwer”,“poui”,“fdgh”}

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

using namespace std;

vector<string> split (const string &s, char delim) {
    vector<string> result;
    stringstream ss (s);
    string item;

    while (getline (ss, item, delim)) {
        result.push_back (item);
    }

    return result;
}

int main() {
    string str = "adsf+qwer+poui+fdgh";
    vector<string> v = split (str, '+');

    for (auto i : v) cout << i << endl;

    return 0;
}

**Output**
adsf
qwer
poui
fdgh