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

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);
}

其他回答

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。

作为奖励,这里有一个分割函数和宏的代码示例,很容易使用,你可以在其中选择容器类型:

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

#define split(str, delim, type) (split_fn<type<std::string>>(str, delim))
 
template <typename Container>
Container split_fn(const std::string& str, char delim = ' ') {
    Container cont{};
    std::size_t current, previous = 0;
    current = str.find(delim);
    while (current != std::string::npos) {
        cont.push_back(str.substr(previous, current - previous));
        previous = current + 1;
        current = str.find(delim, previous);
    }
    cont.push_back(str.substr(previous, current - previous));
    
    return cont;
}

int main() {
    
    auto test = std::string{"This is a great test"};
    auto res = split(test, ' ', std::vector);
    
    for(auto &i : res) {
        std::cout << i << ", "; // "this", "is", "a", "great", "test"
    }
    
    
    return 0;
}

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;
}

我得到这个解。这很简单,所有的打印/值都在循环中(循环后不需要检查)。

#include <iostream>
#include <string>

using std::cout;
using std::string;

int main() {
    string s = "it-+is-+working!";
    string d = "-+";

    int firstFindI = 0;
    int secendFindI = 0;
    while (secendFindI != string::npos)
    {
        secendFindI = s.find(d, firstFindI);
        cout << s.substr(firstFindI, secendFindI - firstFindI) << "\n"; // print sliced part
        firstFindI = secendFindI + d.size(); // add to the search index
    }
}

感谢@SteveWard改进了这个答案。

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