将 std：：string 拆分为向量<string>的正确方法

Question

将字符串拆分为字符串向量的正确方法是什么？分隔符为空格或逗号。

Answer 1

一个方便的方法是boost的字符串算法库。

#include <boost/algorithm/string/classification.hpp> // Include boost::for is_any_of
#include <boost/algorithm/string/split.hpp> // Include for boost::split
// ...
std::vector<std::string> words;
std::string s;
boost::split(words, s, boost::is_any_of(", "), boost::token_compress_on);

Answer 2

对于空格分隔的字符串，您可以这样做：

std::string s = "What is the right way to split a string into a vector of strings";
std::stringstream ss(s);
std::istream_iterator<std::string> begin(ss);
std::istream_iterator<std::string> end;
std::vector<std::string> vstrings(begin, end);
std::copy(vstrings.begin(), vstrings.end(), std::ostream_iterator<std::string>(std::cout, "n"));

输出：

What
is
the
right
way
to
split
a
string
into
a
vector
of
strings

<小时 />

同时包含逗号和空格的字符串

struct tokens: std::ctype<char> 
{
    tokens(): std::ctype<char>(get_table()) {}
 
    static std::ctype_base::mask const* get_table()
    {
        typedef std::ctype<char> cctype;
        static const cctype::mask *const_rc= cctype::classic_table();
 
        static cctype::mask rc[cctype::table_size];
        std::memcpy(rc, const_rc, cctype::table_size * sizeof(cctype::mask));
 
        rc[','] = std::ctype_base::space; 
        rc[' '] = std::ctype_base::space; 
        return &rc[0];
    }
};
 
std::string s = "right way, wrong way, correct way";
std::stringstream ss(s);
ss.imbue(std::locale(std::locale(), new tokens()));
std::istream_iterator<std::string> begin(ss);
std::istream_iterator<std::string> end;
std::vector<std::string> vstrings(begin, end);
std::copy(vstrings.begin(), vstrings.end(), std::ostream_iterator<std::string>(std::cout, "n"));

输出：

right
way
wrong
way
correct
way

Answer 3

您可以将 getline 与分隔符一起使用：

string s, tmp; 
stringstream ss(s);
vector<string> words;
while(getline(ss, tmp, ',')){
    words.push_back(tmp);
    .....
}

Answer 4

vector<string> split(string str, string token){
    vector<string>result;
    while(str.size()){
        int index = str.find(token);
        if(index!=string::npos){
            result.push_back(str.substr(0,index));
            str = str.substr(index+token.size());
            if(str.size()==0)result.push_back(str);
        }else{
            result.push_back(str);
            str = "";
        }
    }
    return result;
}

split("1,2,3"，"，"( ==> ["1"，"2"，"3"]

split("1,2，"，"，"( ==> ["1"，"2"，"]

split("1token2token3"，"token"( ==> ["1"，"2"，"3"]

Answer 5

如果字符串同时包含空格和逗号，则可以使用字符串类函数

found_index = myString.find_first_of(delims_str, begin_index) 

在一个循环中。检查 ！= npos 并插入到向量中。如果你更喜欢老派，你也可以使用C的

strtok() 

方法。

Answer 6

std::vector<std::string> split(std::string text, char delim) {
    std::string line;
    std::vector<std::string> vec;
    std::stringstream ss(text);
    while(std::getline(ss, line, delim)) {
        vec.push_back(line);
    }
    return vec;
}

split("String will be split", ' ') -> {"String", "will", "be", "split"}

split("Hello, how are you?", ',') -> {"Hello", "how are you?"}

编辑：这是我做的一件事，这可以使用多字符分隔符，尽管我不是 100% 确定它是否总是有效：

std::vector<std::string> split(std::string text, std::string delim) {
    std::vector<std::string> vec;
    size_t pos = 0, prevPos = 0;
    while (1) {
        pos = text.find(delim, prevPos);
        if (pos == std::string::npos) {
            vec.push_back(text.substr(prevPos));
            return vec;
        }
        vec.push_back(text.substr(prevPos, pos - prevPos));
        prevPos = pos + delim.length();
    }
}

Answer 7

来自 Techie Delight 的调整版本：

#include <string>
#include <vector>
std::vector<std::string> split(const std::string& str, char delim) {
    std::vector<std::string> strings;
    size_t start;
    size_t end = 0;
    while ((start = str.find_first_not_of(delim, end)) != std::string::npos) {
        end = str.find(delim, start);
        strings.push_back(str.substr(start, end - start));
    }
    return strings;
}

Answer 8

这是我

的变体，它的工作方式有点像 PHP 中的爆炸函数，我们提供给定的字符串和分隔符列表。

std::vector< std::string > explode(const std::string& data, const std::string& delimiters) {
    auto is_delim = [&](auto & c) { return delimiters.find(c) != std::string::npos; };
    std::vector< std::string > result;
    for (std::string::size_type i(0), len(data.length()), pos(0); i <= len; i++) {
        if (is_delim(data[i]) || i == len) {
            auto tok = data.substr(pos, i - pos);
            if ( !tok.empty() )
                result.push_back( tok );
            pos = i + 1;
        }
    } return result;
}

使用示例

std::string test_delimiters("hello, there is lots of, delimiters, that may be even together,  ");
auto dem_res = explode(test_delimiters, " ,"); // space or comma
for (auto word : dem_res) {
    std::cout << word << 'n';
} std::cout << "endn";

输出：

hello
there
is
lots
of
delimiters
that
may
be
even
together
end

Answer 9

我做了这个自定义函数，它将线转换为矢量

#include <iostream>
#include <vector>
#include <ctime>
#include <string>
using namespace std;
int main(){
    string line;
    getline(cin, line);
    int len = line.length();
    vector<string> subArray;
    for (int j = 0, k = 0; j < len; j++) {
        if (line[j] == ' ') {
            string ch = line.substr(k, j - k);
            k = j+1;
            subArray.push_back(ch);
        }
        if (j == len - 1) {
            string ch = line.substr(k, j - k+1);
            subArray.push_back(ch);
        }
    }
    return 0;
}

Answer 10

这是 roach 解决方案的修改版本，它基于一串单字符分隔符 + 支持压缩重复分隔符的选项。

std::vector<std::string> split(std::string text, std::string delim, bool compress) 
{
    std::vector<std::string> vec;
    size_t pos = 0, prevPos = 0;
    while (1) 
    {
        pos = text.find_first_of(delim, prevPos);
        while(compress) 
        {
            if( prevPos == pos )
                prevPos++;
            else
                break;
            pos = text.find_first_of(delim, prevPos);
        }
        if (pos == std::string::npos) {
            if(prevPos != text.size())
                vec.push_back(text.substr(prevPos));
            return vec;
        }
        vec.push_back(text.substr(prevPos, pos - prevPos));
        prevPos = pos + 1;
    }
}

不压缩的示例：

std::string s = "  1.2  foo@foo . ";
auto res = split(s, ".@ ", false);
    for(auto i : res)
        std::cout << "string {" << i << "}" << std::endl;

输出：

string {}
string {}
string {1}
string {2}
string {}
string {foo}
string {foo}
string {}
string {}

带压缩split(s, ".@ ", true);

string {1}
string {2}
string {foo}
string {foo}

Answer 11

这是一个函数，它将string拆分为vector但它在输出vector中不包含空字符串。

vector<string> split(string str, string token) {
    vector<string> result;
    while (str.size()) {
        int index = str.find(token);
        string substr;
        if ((substr = str.substr(0, index)) == "") {
            str = str.substr(index + token.size());
        } else if (index != string::npos) {
            result.push_back(substr);
            str = str.substr(index + token.size());
        } else {
            result.push_back(str);
            str = "";
        }
    }
    return result;
}

注：以上内容改编自这个答案。

Answer 12

用法

void test() {
    string a = "hello : world : ok : fine";
    auto r = split(a, " : ", 2);
    for (auto e: r) {
        cout << e << endl;
    }
}

static inline std::vector<std::string> split(const std::string &str, const std::string &delimiter = " ", const int max_elements = 0) {
    std::vector<std::string> tokens;
    std::string::size_type start_index = 0;
    while (true) {
        std::string::size_type next_index = str.find(delimiter, start_index);
        if (next_index == std::string::npos) {
            tokens.push_back(str.substr(start_index));
            break;
        } else {
            tokens.push_back(str.substr(start_index, next_index - start_index));
            start_index = next_index + delimiter.length();
        }
        if (max_elements > 0 && tokens.size() == max_elements - 1) {
            tokens.push_back(str.substr(start_index));
            break;
        }
    }
    return tokens;
}