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

这与其他答案相似,但它使用了string_view。这些是原始字符串的视图。类似于c++20的例子。虽然这将是一个c++17的例子。(编辑以跳过空匹配)

#include <algorithm>
#include <iostream>
#include <string_view>
#include <vector>
std::vector<std::string_view> split(std::string_view buffer,
                                    const std::string_view delimeter = " ") {
  std::vector<std::string_view> ret{};
  std::decay_t<decltype(std::string_view::npos)> pos{};
  while ((pos = buffer.find(delimeter)) != std::string_view::npos) {
    const auto match = buffer.substr(0, pos);
    if (!match.empty()) ret.push_back(match);
    buffer = buffer.substr(pos + delimeter.size());
  }
  if (!buffer.empty()) ret.push_back(buffer);
  return ret;
}
int main() {
  const auto split_values = split("1 2 3 4 5 6 7 8 9     10 ");
  std::for_each(split_values.begin(), split_values.end(),
                [](const auto& str) { std::cout << str << '\n'; });
  return split_values.size();
}

该方法使用std::string::find,而不改变原始字符串,记住前一个子字符串标记的开始和结束。

#include <iostream>
#include <string>

int main()
{
    std::string s = "scott>=tiger";
    std::string delim = ">=";

    auto start = 0U;
    auto end = s.find(delim);
    while (end != std::string::npos)
    {
        std::cout << s.substr(start, end - start) << std::endl;
        start = end + delim.length();
        end = s.find(delim, start);
    }

    std::cout << s.substr(start, end);
}

我查看了答案,没有看到一个基于迭代器的方法可以被送入范围循环,所以我做了一个。

这使用了c++ 17 string_views,所以它不应该分配字符串的副本。

struct StringSplit
{
    struct Iterator
    {
        size_t tokenStart_ = 0;
        size_t tokenEnd_ = 0;
        std::string str_;
        std::string_view view_;
        std::string delimiter_;
        bool done_ = false;

        Iterator()
        {
            // End iterator.
            done_ = true;
        }

        Iterator(std::string str, std::string delimiter)
            : str_{std::move(str)}, view_{str_}, delimiter_{
                                                     std::move(delimiter)}
        {
            tokenEnd_ = view_.find(delimiter_, tokenStart_);
        }

        std::string_view operator*()
        {
            return view_.substr(tokenStart_, tokenEnd_ - tokenStart_);
        }

        Iterator &operator++()
        {
            if (tokenEnd_ == std::string::npos)
            {
                done_ = true;
                return *this;
            }

            tokenStart_ = tokenEnd_ + delimiter_.size();
            tokenEnd_ = view_.find(delimiter_, tokenStart_);
            return *this;
        }

        bool operator!=(Iterator &other)
        {
            // We only check if both points to the end.
            if (done_ && other.done_)
            {
                return false;
            }

            return true;
        }
    };

    Iterator beginIter_;

    StringSplit(std::string str, std::string delim)
        : beginIter_{std::move(str), std::move(delim)}
    {
    }

    Iterator begin()
    {
        return beginIter_;
    }

    Iterator end()
    {
        return Iterator{};
    }
};

示例用法如下:

int main()
{
    for (auto token : StringSplit{"<>foo<>bar<><>bar<><>baz<><>", "<>"})
    {
        std::cout << "TOKEN: '" << token << "'" << std::endl;
    }
}

打印:

TOKEN: ''
TOKEN: 'foo'
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'baz'
TOKEN: ''
TOKEN: ''

它正确地处理字符串开头和结尾的空项。

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。