538

我正在使用以下内容在 C++ 中解析一个字符串:

using namespace std;

string parsed,input="text to be parsed";
stringstream input_stringstream(input);

if (getline(input_stringstream,parsed,' '))
{
     // do some processing.
}

使用单个字符定界符进行解析很好。但是,如果我想使用字符串作为分隔符怎么办。

示例:我想拆分:

scott>=tiger

>=作为分隔符,这样我就可以得到斯科特和老虎。

4

29 回答 29

829

您可以使用该std::string::find()函数查找字符串分隔符的位置,然后用于std::string::substr()获取令牌。

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)函数返回字符串中第一次出现的位置str,或者npos如果未找到该字符串。

  • substr(size_t pos = 0, size_t n = npos)函数返回对象的子字符串,从 positionpos和 length开始npos


如果您有多个分隔符,则在提取一个标记后,可以将其删除(包括分隔符)以继续进行后续提取(如果要保留原始字符串,只需使用s = s.substr(pos + delimiter.length());):

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

这样您就可以轻松地循环获取每个令牌。

完整示例

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
于 2013-01-10T19:53:17.483 回答
108

此方法std::string::find通过记住前一个子字符串标记的开头和结尾来使用而不改变原始字符串。

#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);
}
于 2013-01-10T21:20:22.690 回答
91

对于字符串分隔符

根据字符串分隔符拆分字符串。如"adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih"根据字符串分隔符分割字符串"-+",输出为{"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;
}


输出

广告
qwret
nvfkbdsj
正值
dfjrleih




对于单个字符分隔符

根据字符分隔符拆分字符串。比如"adsf+qwer+poui+fdgh"用分隔符分割字符串"+"会输出{"adsf", "qwer", "poui", "fdg"h}

#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;
}


输出

广告
qwer
呸呸呸
fdgh
于 2017-10-25T11:54:31.377 回答
61

您可以使用 next 函数来拆分字符串:

vector<string> split(const string& str, const string& delim)
{
    vector<string> tokens;
    size_t prev = 0, pos = 0;
    do
    {
        pos = str.find(delim, prev);
        if (pos == string::npos) pos = str.length();
        string token = str.substr(prev, pos-prev);
        if (!token.empty()) tokens.push_back(token);
        prev = pos + delim.length();
    }
    while (pos < str.length() && prev < str.length());
    return tokens;
}
于 2016-05-26T07:25:41.013 回答
29

您也可以为此使用正则表达式:

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;
}

并像这样使用它:

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

std::vector<std::string> split(const std::string str, const std::string regex_str)
{   // a yet more concise form!
    return { std::sregex_token_iterator(str.begin(), str.end(), std::regex(regex_str), -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;
    }
}

在线玩!http://cpp.sh/9sumb

您可以像平常一样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拆分。
它也简洁和 C++11!

于 2020-11-18T03:46:15.923 回答
28

使用 C++20 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;
    }
}

请参阅:
https ://stackoverflow.com/a/48403210/10771848
https://en.cppreference.com/w/cpp/ranges/split_view

于 2021-06-24T19:24:08.650 回答
22

此代码从文本中拆分行,并将每个人添加到向量中。

vector<string> split(char *phrase, string delimiter){
    vector<string> list;
    string s = string(phrase);
    size_t pos = 0;
    string token;
    while ((pos = s.find(delimiter)) != string::npos) {
        token = s.substr(0, pos);
        list.push_back(token);
        s.erase(0, pos + delimiter.length());
    }
    list.push_back(s);
    return list;
}

调用者:

vector<string> listFilesMax = split(buffer, "\n");
于 2017-06-12T08:54:29.097 回答
19

strtok允许您传入多个字符作为分隔符。我敢打赌,如果您传入 ">=" 您的示例字符串将被正确拆分(即使 > 和 = 被视为单独的分隔符)。

编辑如果您不想使用c_str()从字符串转换为 char*,您可以使用substrfind_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());
}
于 2013-01-10T19:18:35.223 回答
11

答案已经存在,但是选择答案使用擦除功能非常昂贵,想想一些非常大的字符串(以 MB 为单位)。因此我使用以下功能。

vector<string> split(const string& i_str, const string& i_delim)
{
    vector<string> result;
    
    size_t found = i_str.find(i_delim);
    size_t startIndex = 0;

    while(found != string::npos)
    {
        result.push_back(string(i_str.begin()+startIndex, i_str.begin()+found));
        startIndex = found + i_delim.size();
        found = i_str.find(i_delim, startIndex);
    }
    if(startIndex != i_str.size())
        result.push_back(string(i_str.begin()+startIndex, i_str.end()));
    return result;      
}
于 2019-08-04T13:17:00.263 回答
6

我会用boost::tokenizer. 这是解释如何制作适当的标记器功能的文档:http: //www.boost.org/doc/libs/1_52_0/libs/tokenizer/tokenizerfunction.htm

这是适合您的情况的一种。

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';
}
于 2013-01-10T19:40:28.920 回答
6

这是我对此的看法。它处理边缘情况并采用可选参数从结果中删除空条目。

bool endsWith(const std::string& s, const std::string& suffix)
{
    return s.size() >= suffix.size() &&
           s.substr(s.size() - suffix.size()) == suffix;
}

std::vector<std::string> split(const std::string& s, const std::string& delimiter, const bool& removeEmptyEntries = false)
{
    std::vector<std::string> tokens;

    for (size_t start = 0, end; start < s.length(); start = end + delimiter.length())
    {
         size_t position = s.find(delimiter, start);
         end = position != string::npos ? position : s.length();

         std::string token = s.substr(start, end - start);
         if (!removeEmptyEntries || !token.empty())
         {
             tokens.push_back(token);
         }
    }

    if (!removeEmptyEntries &&
        (s.empty() || endsWith(s, delimiter)))
    {
        tokens.push_back("");
    }

    return tokens;
}

例子

split("a-b-c", "-"); // [3]("a","b","c")

split("a--c", "-"); // [3]("a","","c")

split("-b-", "-"); // [3]("","b","")

split("--c--", "-"); // [5]("","","c","","")

split("--c--", "-", true); // [1]("c")

split("a", "-"); // [1]("a")

split("", "-"); // [1]("")

split("", "-", true); // [0]()
于 2017-05-24T10:22:38.533 回答
6

这对于字符串(或单个字符)分隔符应该非常有效。不要忘记包括#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标记。第二个 while 循环跳过分隔符的其余部分并在下一个标记的开头停止。

于 2019-11-06T22:00:16.320 回答
4

这是一个完整的方法,可以在任何分隔符上拆分字符串并返回切碎的字符串的向量。

这是对 ryanbwork 答案的改编。if(token != mystring)但是,如果您的字符串中有重复元素,他的检查:会给出错误的结果。这是我对这个问题的解决方案。

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;
}
于 2019-07-11T14:48:59.320 回答
4

一个非常简单/天真的方法:

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;
}

或者您可以使用 boost 库拆分功能:

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

或者你可以试试 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);
于 2020-09-07T09:00:58.753 回答
3

由于这是最受好评的 Stack Overflow Google 搜索结果C++ split string或类似结果,因此我将发布一个完整的、复制/粘贴可运行示例,显示这两种方法。

splitString用途stringstream(在大多数情况下可能是更好、更容易的选择)

splitString2使用findsubstr(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);
}
于 2020-10-10T03:34:12.893 回答
3

另一个答案:这里我使用的是find_first_not_of字符串函数,它返回与 delim 中指定的任何字符都不匹配的第一个字符的位置。

size_t find_first_not_of(const string& delim, size_t pos = 0) const noexcept;

例子:

int main()
{
    size_t start = 0, end = 0;
    std::string str = "scott>=tiger>=cat";
    std::string delim = ">=";
    while ((start = str.find_first_not_of(delim, end)) != std::string::npos)
    {
        end = str.find(delim, start); // finds the 'first' occurance from the 'start'
        std::cout << str.substr(start, end - start)<<std::endl; // extract substring
    }
    return 0;
}

输出:

    scott
    tiger
    cat
于 2021-03-03T12:25:43.797 回答
3

我做这个解决方案。这很简单,所有打印/值都在循环中(循环后无需检查)。

#include <iostream>
#include <string>

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

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

    int firstFindI = 0;
    int secendFindI = s.find(d, 0); // find if have any at all
    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
    }

}

此解决方案的唯一缺点是在开始时进行两次搜索。

于 2021-03-08T18:52:42.717 回答
2

这与其他答案类似,但它使用的是string_view. 所以这些只是原始字符串的视图。类似于 c++20 示例。虽然这将是一个 c++17 示例。(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();
}
于 2021-08-09T22:12:10.107 回答
2

以防万一将来有人想要Vincenzo Pii答案的开箱即用功能

#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,如果字符串的开头或结尾有分隔符,该函数不会返回空字符串

于 2021-09-16T16:16:34.513 回答
1

如果您不想修改字符串(如 Vincenzo Pii 的回答)并且还想输出最后一个标记,您可能需要使用这种方法:

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;
}
于 2017-05-23T09:37:51.357 回答
1
std::vector<std::string> parse(std::string str,std::string delim){
    std::vector<std::string> tokens;
    char *str_c = strdup(str.c_str()); 
    char* token = NULL;

    token = strtok(str_c, delim.c_str()); 
    while (token != NULL) { 
        tokens.push_back(std::string(token));  
        token = strtok(NULL, delim.c_str()); 
    }

    delete[] str_c;

    return tokens;
}
于 2020-05-27T17:34:43.557 回答
1

这是一个简洁的拆分函数。我决定让背靠背分隔符作为空字符串返回,但您可以轻松检查子字符串是否为空,如果是则不将其添加到向量中。

#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;

}
于 2021-06-08T04:38:14.423 回答
0
#include<iostream>
#include<algorithm>
using namespace std;

int split_count(string str,char delimit){
return count(str.begin(),str.end(),delimit);
}

void split(string str,char delimit,string res[]){
int a=0,i=0;
while(a<str.size()){
res[i]=str.substr(a,str.find(delimit));
a+=res[i].size()+1;
i++;
}
}

int main(){

string a="abc.xyz.mno.def";
int x=split_count(a,'.')+1;
string res[x];
split(a,'.',res);

for(int i=0;i<x;i++)
cout<<res[i]<<endl;
  return 0;
}

PS:仅当拆分后字符串的长度相等时才有效

于 2018-01-29T08:15:15.383 回答
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;
}
于 2020-03-13T17:19:02.967 回答
0

作为奖励,这是一个易于使用的拆分函数和宏的代码示例,您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;
}
于 2020-11-12T15:38:14.970 回答
0
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.push_back(std::forward<T>(t)), void()) {
    c.push_back(std::forward<T>(t));
}
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.insert(std::forward<T>(t)), void()) {
    c.insert(std::forward<T>(t));
}
template<typename Container>
Container splitR(const std::string& input, const std::string& delims) {
    Container out;
    size_t delims_len = delims.size();
    auto begIdx = 0u;
    auto endIdx = input.find(delims, begIdx);
    if (endIdx == std::string::npos && input.size() != 0u) {
        insert_in_container(out, input);
    }
    else {
        size_t w = 0;
        while (endIdx != std::string::npos) {
            w = endIdx - begIdx;
            if (w != 0) insert_in_container(out, input.substr(begIdx, w));
            begIdx = endIdx + delims_len;
            endIdx = input.find(delims, begIdx);
        }
        w = input.length() - begIdx;
        if (w != 0) insert_in_container(out, input.substr(begIdx, w));
    }
    return out;
}
于 2021-02-24T18:35:10.213 回答
0

我使用指针算术。如果您使用 char delim 来满足字符串分隔符的 inner while ,则只需简单地删除 inner while 。我希望它是正确的。如果您发现任何错误或改进,请发表评论。

std::vector<std::string> split(std::string s, std::string delim)
{
    char *p = &s[0];
    char *d = &delim[0];
    std::vector<std::string> res = {""};

    do
    {
        bool is_delim = true;
        char *pp = p;
        char *dd = d;
        while (*dd && is_delim == true)
            if (*pp++ != *dd++)
                is_delim = false;

        if (is_delim)
        {
            p = pp - 1;
            res.push_back("");
        }
        else
            *(res.rbegin()) += *p;
    } while (*p++);

    return res;
}
于 2021-05-08T00:58:12.093 回答
-1

从 C++11 开始,它可以这样完成:

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) ); 

笔记:

于 2021-02-10T12:44:18.093 回答
-4
std::vector<std::string> split(const std::string& s, char c) {
  std::vector<std::string> v;
  unsigned int ii = 0;
  unsigned int j = s.find(c);
  while (j < s.length()) {
    v.push_back(s.substr(i, j - i));
    i = ++j;
    j = s.find(c, j);
    if (j >= s.length()) {
      v.push_back(s.substr(i, s,length()));
      break;
    }
  }
  return v;
}
于 2017-02-27T20:45:31.433 回答