如何迭代由空格分隔的单词组成的字符串中的单词？
注意，我对C字符串函数或那种字符操作/访问不感兴趣。比起效率，我更喜欢优雅。我当前的解决方案：
#include <iostream>
#include <sstream>
#include <string>
using namespace std;
int main() {
string s = "Somewhere down the road";
istringstream iss(s);
do {
string subs;
iss >> subs;
cout << "Substring: " << subs << endl;
} while (iss);
}
当前回答
最小的解决方案是一个函数，它将std:：字符串和一组分隔符（作为std:：string）作为输入，并返回std:：：字符串的std:：向量。
#include <string>
#include <vector>
std::vector<std::string>
tokenize(const std::string& str, const std::string& delimiters)
{
using ssize_t = std::string::size_type;
const ssize_t str_ln = str.length();
ssize_t last_pos = 0;
// container for the extracted tokens
std::vector<std::string> tokens;
while (last_pos < str_ln) {
// find the position of the next delimiter
ssize_t pos = str.find_first_of(delimiters, last_pos);
// if no delimiters found, set the position to the length of string
if (pos == std::string::npos)
pos = str_ln;
// if the substring is nonempty, store it in the container
if (pos != last_pos)
tokens.emplace_back(str.substr(last_pos, pos - last_pos));
// scan past the previous substring
last_pos = pos + 1;
}
return tokens;
}
用法示例：
#include <iostream>
int main()
{
std::string input_str = "one + two * (three - four)!!---! ";
const char* delimiters = "! +- (*)";
std::vector<std::string> tokens = tokenize(input_str, delimiters);
std::cout << "input = '" << input_str << "'\n"
<< "delimiters = '" << delimiters << "'\n"
<< "nr of tokens found = " << tokens.size() << std::endl;
for (const std::string& tk : tokens) {
std::cout << "token = '" << tk << "'\n";
}
return 0;
}
其他回答
虽然有一些答案提供了C++20解决方案，但自从发布以来，已经做了一些更改，并将其作为缺陷报告应用于C++20。正因为如此，解决方案变得更短、更好：
#include <iostream>
#include <ranges>
#include <string_view>
namespace views = std::views;
using str = std::string_view;
constexpr str text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit.";
auto splitByWords(str input) {
return input
| views::split(' ')
| views::transform([](auto &&r) -> str {
return {r.begin(), r.end()};
});
}
auto main() -> int {
for (str &&word : splitByWords(text)) {
std::cout << word << '\n';
}
}
到今天为止，它仍然只在GCC的主干分支（Godbolt链接）上可用。它基于两个更改：P1391迭代器构造函数用于std:：string_view和P2210 DR修复std:：views:：split以保留范围类型。
在C++23中，不需要任何转换样板，因为P1989向std:：string_view:添加了一个范围构造函数
#include <iostream>
#include <ranges>
#include <string_view>
namespace views = std::views;
constexpr std::string_view text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit.";
auto main() -> int {
for (std::string_view&& word : text | views::split(' ')) {
std::cout << word << '\n';
}
}
（螺栓连杆）
这是一个顶级答案的扩展。它现在支持设置返回元素的最大数量N。字符串的最后一位将在第N个元素中结束。MAXELEMENTS参数是可选的，如果设置为默认值0，它将返回无限数量的元素。：-）
.h:
class Myneatclass {
public:
static std::vector<std::string>& split(const std::string &s, char delim, std::vector<std::string> &elems, const size_t MAXELEMENTS = 0);
static std::vector<std::string> split(const std::string &s, char delim, const size_t MAXELEMENTS = 0);
};
.cpp：
std::vector<std::string>& Myneatclass::split(const std::string &s, char delim, std::vector<std::string> &elems, const size_t MAXELEMENTS) {
std::stringstream ss(s);
std::string item;
while (std::getline(ss, item, delim)) {
elems.push_back(item);
if (MAXELEMENTS > 0 && !ss.eof() && elems.size() + 1 >= MAXELEMENTS) {
std::getline(ss, item);
elems.push_back(item);
break;
}
}
return elems;
}
std::vector<std::string> Myneatclass::split(const std::string &s, char delim, const size_t MAXELEMENTS) {
std::vector<std::string> elems;
split(s, delim, elems, MAXELEMENTS);
return elems;
}
#include <iostream>
#include <string>
#include <sstream>
#include <algorithm>
#include <iterator>
#include <vector>
int main() {
using namespace std;
int n=8;
string sentence = "10 20 30 40 5 6 7 8";
istringstream iss(sentence);
vector<string> tokens;
copy(istream_iterator<string>(iss),
istream_iterator<string>(),
back_inserter(tokens));
for(int i=0;i<n;i++){
cout<<tokens.at(i);
}
}
仅为方便：
template<class V, typename T>
bool in(const V &v, const T &el) {
return std::find(v.begin(), v.end(), el) != v.end();
}
基于多个分隔符的实际拆分：
std::vector<std::string> split(const std::string &s,
const std::vector<char> &delims) {
std::vector<std::string> res;
auto stuff = [&delims](char c) { return !in(delims, c); };
auto space = [&delims](char c) { return in(delims, c); };
auto first = std::find_if(s.begin(), s.end(), stuff);
while (first != s.end()) {
auto last = std::find_if(first, s.end(), space);
res.push_back(std::string(first, last));
first = std::find_if(last + 1, s.end(), stuff);
}
return res;
}
用法：
int main() {
std::string s = " aaa, bb cc ";
for (auto el: split(s, {' ', ','}))
std::cout << el << std::endl;
return 0;
}
#include <iostream>
#include <vector>
using namespace std;
int main() {
string str = "ABC AABCD CDDD RABC GHTTYU FR";
str += " "; //dirty hack: adding extra space to the end
vector<string> v;
for (int i=0; i<(int)str.size(); i++) {
int a, b;
a = i;
for (int j=i; j<(int)str.size(); j++) {
if (str[j] == ' ') {
b = j;
i = j;
break;
}
}
v.push_back(str.substr(a, b-a));
}
for (int i=0; i<v.size(); i++) {
cout<<v[i].size()<<" "<<v[i]<<endl;
}
return 0;
}
