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

这是一个简洁的分裂函数。我决定让背靠背分隔符返回为空字符串,但您可以很容易地检查子字符串是否为空,如果是,则不将其添加到向量。

#include <vector>
#include <string>
using namespace std;



vector<string> split(string to_split, string delimiter) {
    size_t pos = 0;
    vector<string> matches{};
    do {
        pos = to_split.find(delimiter);
        int change_end;
        if (pos == string::npos) {
            pos = to_split.length() - 1;
            change_end = 1;
        }
        else {
            change_end = 0;
        }
        matches.push_back(to_split.substr(0, pos+change_end));
        
        to_split.erase(0, pos+1);

    }
    while (!to_split.empty());
    return matches;

}

其他回答

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

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。

一种非常简单/幼稚的方法:

vector<string> words_seperate(string s){
    vector<string> ans;
    string w="";
    for(auto i:s){
        if(i==' '){
           ans.push_back(w);
           w="";
        }
        else{
           w+=i;
        }
    }
    ans.push_back(w);
    return ans;
}

或者你可以使用boost库拆分函数:

vector<string> result; 
boost::split(result, input, boost::is_any_of("\t"));

或者你可以尝试TOKEN或strtok:

char str[] = "DELIMIT-ME-C++"; 
char *token = strtok(str, "-"); 
while (token) 
{ 
    cout<<token; 
    token = strtok(NULL, "-"); 
} 

或者你可以这样做:

char split_with=' ';
vector<string> words;
string token; 
stringstream ss(our_string);
while(getline(ss , token , split_with)) words.push_back(token);

从c++ 11开始,它可以这样做:

std::vector<std::string> splitString(const std::string& str,
                                     const std::regex& regex)
{
  return {std::sregex_token_iterator{str.begin(), str.end(), regex, -1}, 
          std::sregex_token_iterator() };
} 

// usually we have a predefined set of regular expressions: then
// let's build those only once and re-use them multiple times
static const std::regex regex1(R"some-reg-exp1", std::regex::optimize);
static const std::regex regex2(R"some-reg-exp2", std::regex::optimize);
static const std::regex regex3(R"some-reg-exp3", std::regex::optimize);

string str = "some string to split";
std::vector<std::string> tokens( splitString(str, regex1) ); 

注:

这是对这个答案的一个小小的改进 参见std::regex_constants::optimize使用的优化技术

功能:

std::vector<std::string> WSJCppCore::split(const std::string& sWhat, const std::string& sDelim) {
    std::vector<std::string> vRet;
    size_t nPos = 0;
    size_t nLen = sWhat.length();
    size_t nDelimLen = sDelim.length();
    while (nPos < nLen) {
        std::size_t nFoundPos = sWhat.find(sDelim, nPos);
        if (nFoundPos != std::string::npos) {
            std::string sToken = sWhat.substr(nPos, nFoundPos - nPos);
            vRet.push_back(sToken);
            nPos = nFoundPos + nDelimLen;
            if (nFoundPos + nDelimLen == nLen) { // last delimiter
                vRet.push_back("");
            }
        } else {
            std::string sToken = sWhat.substr(nPos, nLen - nPos);
            vRet.push_back(sToken);
            break;
        }
    }
    return vRet;
}

单元测试:

bool UnitTestSplit::run() {
bool bTestSuccess = true;

    struct LTest {
        LTest(
            const std::string &sStr,
            const std::string &sDelim,
            const std::vector<std::string> &vExpectedVector
        ) {
            this->sStr = sStr;
            this->sDelim = sDelim;
            this->vExpectedVector = vExpectedVector;
        };
        std::string sStr;
        std::string sDelim;
        std::vector<std::string> vExpectedVector;
    };
    std::vector<LTest> tests;
    tests.push_back(LTest("1 2 3 4 5", " ", {"1", "2", "3", "4", "5"}));
    tests.push_back(LTest("|1f|2п|3%^|44354|5kdasjfdre|2", "|", {"", "1f", "2п", "3%^", "44354", "5kdasjfdre", "2"}));
    tests.push_back(LTest("|1f|2п|3%^|44354|5kdasjfdre|", "|", {"", "1f", "2п", "3%^", "44354", "5kdasjfdre", ""}));
    tests.push_back(LTest("some1 => some2 => some3", "=>", {"some1 ", " some2 ", " some3"}));
    tests.push_back(LTest("some1 => some2 => some3 =>", "=>", {"some1 ", " some2 ", " some3 ", ""}));

    for (int i = 0; i < tests.size(); i++) {
        LTest test = tests[i];
        std::string sPrefix = "test" + std::to_string(i) + "(\"" + test.sStr + "\")";
        std::vector<std::string> vSplitted = WSJCppCore::split(test.sStr, test.sDelim);
        compareN(bTestSuccess, sPrefix + ": size", vSplitted.size(), test.vExpectedVector.size());
        int nMin = std::min(vSplitted.size(), test.vExpectedVector.size());
        for (int n = 0; n < nMin; n++) {
            compareS(bTestSuccess, sPrefix + ", element: " + std::to_string(n), vSplitted[n], test.vExpectedVector[n]);
        }
    }

    return bTestSuccess;
}