一些C++20编译器和大多数C++23编译器（range和string_view）

for (auto word : std::views::split("Somewhere down the road", ' '))
        std::cout << std::string_view{ word.begin(), word.end() } << std::endl;

我这样做是因为我需要一种简单的方法来分割字符串和基于c的字符串。。。希望其他人也能发现它很有用。此外，它不依赖令牌，您可以使用字段作为分隔符，这是我需要的另一个键。

我相信可以做一些改进，以进一步提高其优雅度，请尽一切努力

StringSplitter.hpp：

#include <vector>
#include <iostream>
#include <string.h>

using namespace std;

class StringSplit
{
private:
    void copy_fragment(char*, char*, char*);
    void copy_fragment(char*, char*, char);
    bool match_fragment(char*, char*, int);
    int untilnextdelim(char*, char);
    int untilnextdelim(char*, char*);
    void assimilate(char*, char);
    void assimilate(char*, char*);
    bool string_contains(char*, char*);
    long calc_string_size(char*);
    void copy_string(char*, char*);

public:
    vector<char*> split_cstr(char);
    vector<char*> split_cstr(char*);
    vector<string> split_string(char);
    vector<string> split_string(char*);
    char* String;
    bool do_string;
    bool keep_empty;
    vector<char*> Container;
    vector<string> ContainerS;

    StringSplit(char * in)
    {
        String = in;
    }

    StringSplit(string in)
    {
        size_t len = calc_string_size((char*)in.c_str());
        String = new char[len + 1];
        memset(String, 0, len + 1);
        copy_string(String, (char*)in.c_str());
        do_string = true;
    }

    ~StringSplit()
    {
        for (int i = 0; i < Container.size(); i++)
        {
            if (Container[i] != NULL)
            {
                delete[] Container[i];
            }
        }
        if (do_string)
        {
            delete[] String;
        }
    }
};

StringSplitter.cpp：

#include <string.h>
#include <iostream>
#include <vector>
#include "StringSplit.hpp"

using namespace std;

void StringSplit::assimilate(char*src, char delim)
{
    int until = untilnextdelim(src, delim);
    if (until > 0)
    {
        char * temp = new char[until + 1];
        memset(temp, 0, until + 1);
        copy_fragment(temp, src, delim);
        if (keep_empty || *temp != 0)
        {
            if (!do_string)
            {
                Container.push_back(temp);
            }
            else
            {
                string x = temp;
                ContainerS.push_back(x);
            }

        }
        else
        {
            delete[] temp;
        }
    }
}

void StringSplit::assimilate(char*src, char* delim)
{
    int until = untilnextdelim(src, delim);
    if (until > 0)
    {
        char * temp = new char[until + 1];
        memset(temp, 0, until + 1);
        copy_fragment(temp, src, delim);
        if (keep_empty || *temp != 0)
        {
            if (!do_string)
            {
                Container.push_back(temp);
            }
            else
            {
                string x = temp;
                ContainerS.push_back(x);
            }
        }
        else
        {
            delete[] temp;
        }
    }
}

long StringSplit::calc_string_size(char* _in)
{
    long i = 0;
    while (*_in++)
    {
        i++;
    }
    return i;
}

bool StringSplit::string_contains(char* haystack, char* needle)
{
    size_t len = calc_string_size(needle);
    size_t lenh = calc_string_size(haystack);
    while (lenh--)
    {
        if (match_fragment(haystack + lenh, needle, len))
        {
            return true;
        }
    }
    return false;
}

bool StringSplit::match_fragment(char* _src, char* cmp, int len)
{
    while (len--)
    {
        if (*(_src + len) != *(cmp + len))
        {
            return false;
        }
    }
    return true;
}

int StringSplit::untilnextdelim(char* _in, char delim)
{
    size_t len = calc_string_size(_in);
    if (*_in == delim)
    {
        _in += 1;
        return len - 1;
    }

    int c = 0;
    while (*(_in + c) != delim && c < len)
    {
        c++;
    }

    return c;
}

int StringSplit::untilnextdelim(char* _in, char* delim)
{
    int s = calc_string_size(delim);
    int c = 1 + s;

    if (!string_contains(_in, delim))
    {
        return calc_string_size(_in);
    }
    else if (match_fragment(_in, delim, s))
    {
        _in += s;
        return calc_string_size(_in);
    }

    while (!match_fragment(_in + c, delim, s))
    {
        c++;
    }

    return c;
}

void StringSplit::copy_fragment(char* dest, char* src, char delim)
{
    if (*src == delim)
    {
        src++;
    }

    int c = 0;
    while (*(src + c) != delim && *(src + c))
    {
        *(dest + c) = *(src + c);
        c++;
    }
    *(dest + c) = 0;
}

void StringSplit::copy_string(char* dest, char* src)
{
    int i = 0;
    while (*(src + i))
    {
        *(dest + i) = *(src + i);
        i++;
    }
}

void StringSplit::copy_fragment(char* dest, char* src, char* delim)
{
    size_t len = calc_string_size(delim);
    size_t lens = calc_string_size(src);

    if (match_fragment(src, delim, len))
    {
        src += len;
        lens -= len;
    }

    int c = 0;
    while (!match_fragment(src + c, delim, len) && (c < lens))
    {
        *(dest + c) = *(src + c);
        c++;
    }
    *(dest + c) = 0;
}

vector<char*> StringSplit::split_cstr(char Delimiter)
{
    int i = 0;
    while (*String)
    {
        if (*String != Delimiter && i == 0)
        {
            assimilate(String, Delimiter);
        }
        if (*String == Delimiter)
        {
            assimilate(String, Delimiter);
        }
        i++;
        String++;
    }

    String -= i;
    delete[] String;

    return Container;
}

vector<string> StringSplit::split_string(char Delimiter)
{
    do_string = true;

    int i = 0;
    while (*String)
    {
        if (*String != Delimiter && i == 0)
        {
            assimilate(String, Delimiter);
        }
        if (*String == Delimiter)
        {
            assimilate(String, Delimiter);
        }
        i++;
        String++;
    }

    String -= i;
    delete[] String;

    return ContainerS;
}

vector<char*> StringSplit::split_cstr(char* Delimiter)
{
    int i = 0;
    size_t LenDelim = calc_string_size(Delimiter);

    while(*String)
    {
        if (!match_fragment(String, Delimiter, LenDelim) && i == 0)
        {
            assimilate(String, Delimiter);
        }
        if (match_fragment(String, Delimiter, LenDelim))
        {
            assimilate(String,Delimiter);
        }
        i++;
        String++;
    }

    String -= i;
    delete[] String;

    return Container;
}

vector<string> StringSplit::split_string(char* Delimiter)
{
    do_string = true;
    int i = 0;
    size_t LenDelim = calc_string_size(Delimiter);

    while (*String)
    {
        if (!match_fragment(String, Delimiter, LenDelim) && i == 0)
        {
            assimilate(String, Delimiter);
        }
        if (match_fragment(String, Delimiter, LenDelim))
        {
            assimilate(String, Delimiter);
        }
        i++;
        String++;
    }

    String -= i;
    delete[] String;

    return ContainerS;
}

示例：

int main(int argc, char*argv[])
{
    StringSplit ss = "This:CUT:is:CUT:an:CUT:example:CUT:cstring";
    vector<char*> Split = ss.split_cstr(":CUT:");

    for (int i = 0; i < Split.size(); i++)
    {
        cout << Split[i] << endl;
    }

    return 0;
}

将输出：

这是一实例cst环

int main(int argc, char*argv[])
{
    StringSplit ss = "This:is:an:example:cstring";
    vector<char*> Split = ss.split_cstr(':');

    for (int i = 0; i < Split.size(); i++)
    {
        cout << Split[i] << endl;
    }

    return 0;
}

int main(int argc, char*argv[])
{
    string mystring = "This[SPLIT]is[SPLIT]an[SPLIT]example[SPLIT]string";
    StringSplit ss = mystring;
    vector<string> Split = ss.split_string("[SPLIT]");

    for (int i = 0; i < Split.size(); i++)
    {
        cout << Split[i] << endl;
    }

    return 0;
}

int main(int argc, char*argv[])
{
    string mystring = "This|is|an|example|string";
    StringSplit ss = mystring;
    vector<string> Split = ss.split_string('|');

    for (int i = 0; i < Split.size(); i++)
    {
        cout << Split[i] << endl;
    }

    return 0;
}

要保留空条目（默认情况下将排除空条目）：

StringSplit ss = mystring;
ss.keep_empty = true;
vector<string> Split = ss.split_string(":DELIM:");

目标是使其类似于C#的Split（）方法，其中拆分字符串非常简单：

String[] Split = 
    "Hey:cut:what's:cut:your:cut:name?".Split(new[]{":cut:"}, StringSplitOptions.None);

foreach(String X in Split)
{
    Console.Write(X);
}

我希望其他人能像我一样觉得这很有用。

我喜欢下面的代码，因为它将结果放入一个向量中，支持字符串作为delim，并控制保持空值。但是，那时候看起来不太好。

#include <ostream>
#include <string>
#include <vector>
#include <algorithm>
#include <iterator>
using namespace std;

vector<string> split(const string& s, const string& delim, const bool keep_empty = true) {
    vector<string> result;
    if (delim.empty()) {
        result.push_back(s);
        return result;
    }
    string::const_iterator substart = s.begin(), subend;
    while (true) {
        subend = search(substart, s.end(), delim.begin(), delim.end());
        string temp(substart, subend);
        if (keep_empty || !temp.empty()) {
            result.push_back(temp);
        }
        if (subend == s.end()) {
            break;
        }
        substart = subend + delim.size();
    }
    return result;
}

int main() {
    const vector<string> words = split("So close no matter how far", " ");
    copy(words.begin(), words.end(), ostream_iterator<string>(cout, "\n"));
}

当然，Boost有一个split（），它的部分功能与此类似。而且，如果“空白”是指任何类型的空白，那么使用Boost的split和is_any_of（）都非常有用。

#include <iostream>
#include <string>
#include <deque>

std::deque<std::string> split(
    const std::string& line, 
    std::string::value_type delimiter,
    bool skipEmpty = false
) {
    std::deque<std::string> parts{};

    if (!skipEmpty && !line.empty() && delimiter == line.at(0)) {
        parts.push_back({});
    }

    for (const std::string::value_type& c : line) {
        if (
            (
                c == delimiter 
                &&
                (skipEmpty ? (!parts.empty() && !parts.back().empty()) : true)
            )
            ||
            (c != delimiter && parts.empty())
        ) {
            parts.push_back({});
        }

        if (c != delimiter) {
            parts.back().push_back(c);
        }
    }

    if (skipEmpty && !parts.empty() && parts.back().empty()) {
        parts.pop_back();
    }

    return parts;
}

void test(const std::string& line) {
    std::cout << line << std::endl;

    std::cout << "skipEmpty=0 |";
    for (const std::string& part : split(line, ':')) {
        std::cout << part << '|';
    }
    std::cout << std::endl;

    std::cout << "skipEmpty=1 |";
    for (const std::string& part : split(line, ':', true)) {
        std::cout << part << '|';
    }
    std::cout << std::endl;

    std::cout << std::endl;
}

int main() {
    test("foo:bar:::baz");
    test("");
    test("foo");
    test(":");
    test("::");
    test(":foo");
    test("::foo");
    test(":foo:");
    test(":foo::");

    return 0;
}

输出：

foo:bar:::baz
skipEmpty=0 |foo|bar|||baz|
skipEmpty=1 |foo|bar|baz|


skipEmpty=0 |
skipEmpty=1 |

foo
skipEmpty=0 |foo|
skipEmpty=1 |foo|

:
skipEmpty=0 |||
skipEmpty=1 |

::
skipEmpty=0 ||||
skipEmpty=1 |

:foo
skipEmpty=0 ||foo|
skipEmpty=1 |foo|

::foo
skipEmpty=0 |||foo|
skipEmpty=1 |foo|

:foo:
skipEmpty=0 ||foo||
skipEmpty=1 |foo|

:foo::
skipEmpty=0 ||foo|||
skipEmpty=1 |foo|

我知道很晚才来参加聚会，但我正在考虑最优雅的方法，如果给你一系列分隔符而不是空格，并且只使用标准库。

以下是我的想法：

要通过分隔符序列将单词拆分为字符串向量，请执行以下操作：

template<class Container>
std::vector<std::string> split_by_delimiters(const std::string& input, const Container& delimiters)
{
    std::vector<std::string> result;

    for (auto current = begin(input) ; current != end(input) ; )
    {
        auto first = find_if(current, end(input), not_in(delimiters));
        if (first == end(input)) break;
        auto last = find_if(first, end(input), is_in(delimiters));
        result.emplace_back(first, last);
        current = last;
    }
    return result;
}

通过提供一系列有效字符，以另一种方式进行拆分：

template<class Container>
std::vector<std::string> split_by_valid_chars(const std::string& input, const Container& valid_chars)
{
    std::vector<std::string> result;

    for (auto current = begin(input) ; current != end(input) ; )
    {
        auto first = find_if(current, end(input), is_in(valid_chars));
        if (first == end(input)) break;
        auto last = find_if(first, end(input), not_in(valid_chars));
        result.emplace_back(first, last);
        current = last;
    }
    return result;
}

is_in和not_in的定义如下：

namespace detail {
    template<class Container>
    struct is_in {
        is_in(const Container& charset)
        : _charset(charset)
        {}

        bool operator()(char c) const
        {
            return find(begin(_charset), end(_charset), c) != end(_charset);
        }

        const Container& _charset;
    };

    template<class Container>
    struct not_in {
        not_in(const Container& charset)
        : _charset(charset)
        {}

        bool operator()(char c) const
        {
            return find(begin(_charset), end(_charset), c) == end(_charset);
        }

        const Container& _charset;
    };

}

template<class Container>
detail::not_in<Container> not_in(const Container& c)
{
    return detail::not_in<Container>(c);
}

template<class Container>
detail::is_in<Container> is_in(const Container& c)
{
    return detail::is_in<Container>(c);
}

对于那个些需要使用字符串分隔符拆分字符串的人，也许可以尝试我的以下解决方案。

std::vector<size_t> str_pos(const std::string &search, const std::string &target)
{
    std::vector<size_t> founds;

    if(!search.empty())
    {
        size_t start_pos = 0;

        while (true)
        {
            size_t found_pos = target.find(search, start_pos);

            if(found_pos != std::string::npos)
            {
                size_t found = found_pos;

                founds.push_back(found);

                start_pos = (found_pos + 1);
            }
            else
            {
                break;
            }
        }
    }

    return founds;
}

std::string str_sub_index(size_t begin_index, size_t end_index, const std::string &target)
{
    std::string sub;

    size_t size = target.length();

    const char* copy = target.c_str();

    for(size_t i = begin_index; i <= end_index; i++)
    {
        if(i >= size)
        {
            break;
        }
        else
        {
            char c = copy[i];

            sub += c;
        }
    }

    return sub;
}

std::vector<std::string> str_split(const std::string &delimiter, const std::string &target)
{
    std::vector<std::string> splits;

    if(!delimiter.empty())
    {
        std::vector<size_t> founds = str_pos(delimiter, target);

        size_t founds_size = founds.size();

        if(founds_size > 0)
        {
            size_t search_len = delimiter.length();

            size_t begin_index = 0;

            for(int i = 0; i <= founds_size; i++)
            {
                std::string sub;

                if(i != founds_size)
                {
                    size_t pos  = founds.at(i);

                    sub = str_sub_index(begin_index, pos - 1, target);

                    begin_index = (pos + search_len);
                }
                else
                {
                    sub = str_sub_index(begin_index, (target.length() - 1), target);
                }

                splits.push_back(sub);
            }
        }
    }

    return splits;
}

这些片段由3个函数组成。坏消息是使用str_split函数，您将需要另外两个函数。是的，这是一大块代码。但好消息是，这两个附加功能可以独立工作，有时也很有用

测试main（）块中的函数如下：

int main()
{
    std::string s = "Hello, world! We need to make the world a better place. Because your world is also my world, and our children's world.";

    std::vector<std::string> split = str_split("world", s);

    for(int i = 0; i < split.size(); i++)
    {
        std::cout << split[i] << std::endl;
    }
}

它将产生：

Hello, 
! We need to make the 
 a better place. Because your 
 is also my 
, and our children's 
.

我认为这不是最有效的代码，但至少它可以工作。希望有帮助。