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

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;
}

其他回答

您可以使用std::string::find()函数来查找字符串分隔符的位置,然后使用std::string::substr()来获取一个令牌。

例子:

std::string s = "scott>=tiger";
std::string delimiter = ">=";
std::string token = s.substr(0, s.find(delimiter)); // token is "scott"

find(const string& str, size_t pos = 0)函数的作用是:返回字符串中str第一次出现的位置,如果没有找到则返回npos。 substr(size_t pos = 0, size_t n = npos)函数的作用是:返回对象的子字符串,从位置pos开始,长度npos。


如果你有多个分隔符,在你提取了一个标记之后,你可以删除它(包括分隔符)以继续后续的提取(如果你想保留原始字符串,只需使用s = s.s substr(pos + delimiter.length());):

s.erase(0, s.find(delimiter) + delimiter.length());

这样就可以轻松地循环获取每个令牌。

完整的示例

std::string s = "scott>=tiger>=mushroom";
std::string delimiter = ">=";

size_t pos = 0;
std::string token;
while ((pos = s.find(delimiter)) != std::string::npos) {
    token = s.substr(0, pos);
    std::cout << token << std::endl;
    s.erase(0, pos + delimiter.length());
}
std::cout << s << std::endl;

输出:

scott
tiger
mushroom

你也可以使用regex:

std::vector<std::string> split(const std::string str, const std::string regex_str)
{
    std::regex regexz(regex_str);
    std::vector<std::string> list(std::sregex_token_iterator(str.begin(), str.end(), regexz, -1),
                                  std::sregex_token_iterator());
    return list;
}

这相当于:

std::vector<std::string> split(const std::string str, const std::string regex_str)
{
    std::sregex_token_iterator token_iter(str.begin(), str.end(), regexz, -1);
    std::sregex_token_iterator end;
    std::vector<std::string> list;
    while (token_iter != end)
    {
        list.emplace_back(*token_iter++);
    }
    return list;
}

像这样使用它:

#include <iostream>
#include <string>
#include <regex>

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

int main()
{
    std::string input_str = "lets split this";
    std::string regex_str = " "; 
    auto tokens = split(input_str, regex_str);
    for (auto& item: tokens)
    {
        std::cout<<item <<std::endl;
    }
}

在网上玩!

您可以简单地使用子字符串、字符等,或者使用实际的正则表达式来进行分割。 它也是简洁的c++ 11!

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';
}

如果你不想修改字符串(就像Vincenzo Pii回答的那样),并且想输出最后一个令牌,你可能想使用这种方法:

inline std::vector<std::string> splitString( const std::string &s, const std::string &delimiter ){
    std::vector<std::string> ret;
    size_t start = 0;
    size_t end = 0;
    size_t len = 0;
    std::string token;
    do{ end = s.find(delimiter,start); 
        len = end - start;
        token = s.substr(start, len);
        ret.emplace_back( token );
        start += len + delimiter.length();
        std::cout << token << std::endl;
    }while ( end != std::string::npos );
    return ret;
}

Strtok允许您传入多个字符作为分隔符。我敢打赌,如果你传入“>=”,你的示例字符串将被正确分割(即使>和=被算作单独的分隔符)。

EDIT如果您不想使用c_str()将字符串转换为char*,您可以使用substr和find_first_of进行标记化。

string token, mystring("scott>=tiger");
while(token != mystring){
  token = mystring.substr(0,mystring.find_first_of(">="));
  mystring = mystring.substr(mystring.find_first_of(">=") + 1);
  printf("%s ",token.c_str());
}