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

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

这是一个完整的方法,它在任何分隔符上分割字符串,并返回分割后的字符串的向量。

这是改编自ryanbwork的答案。然而,他的检查:if(token != mystring)给出错误的结果,如果你的字符串中有重复的元素。这是我对那个问题的解决方案。

vector<string> Split(string mystring, string delimiter)
{
    vector<string> subStringList;
    string token;
    while (true)
    {
        size_t findfirst = mystring.find_first_of(delimiter);
        if (findfirst == string::npos) //find_first_of returns npos if it couldn't find the delimiter anymore
        {
            subStringList.push_back(mystring); //push back the final piece of mystring
            return subStringList;
        }
        token = mystring.substr(0, mystring.find_first_of(delimiter));
        mystring = mystring.substr(mystring.find_first_of(delimiter) + 1);
        subStringList.push_back(token);
    }
    return subStringList;
}

以防将来,有人想跳出Vincenzo Pii答案的盒子函数

#include <vector>
#include <string>


std::vector<std::string> SplitString(
    std::string str,
    std::string delimeter)
{
    std::vector<std::string> splittedStrings = {};
    size_t pos = 0;

    while ((pos = str.find(delimeter)) != std::string::npos)
    {
        std::string token = str.substr(0, pos);
        if (token.length() > 0)
            splittedStrings.push_back(token);
        str.erase(0, pos + delimeter.length());
    }

    if (str.length() > 0)
        splittedStrings.push_back(str);
    return splittedStrings;
}

我还修复了一些错误,以便如果字符串的开头或结尾有分隔符,函数将不会返回空字符串

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());
}

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();
}