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
在处理空格作为分隔符时，使用std:：istream_iterator<T>的明显答案已经给出，并得到了很多支持。当然，元素可能不是用空格分隔，而是用一些分隔符分隔。我没有找到任何答案，只是重新定义了空格的含义，将其称为分隔符，然后使用常规方法。
要改变流对空白的看法，只需使用（std:：istream:：imbue（））将流的std:：locale更改为std:：ctype<char>方面，并定义空白的含义（也可以对std:：：ctype<wchar_t>进行更改，但实际上略有不同，因为std:：actype<char>是表驱动的，而std:：type<wchar_t>是由虚拟函数驱动的）。
#include <iostream>
#include <algorithm>
#include <iterator>
#include <sstream>
#include <locale>
struct whitespace_mask {
std::ctype_base::mask mask_table[std::ctype<char>::table_size];
whitespace_mask(std::string const& spaces) {
std::ctype_base::mask* table = this->mask_table;
std::ctype_base::mask const* tab
= std::use_facet<std::ctype<char>>(std::locale()).table();
for (std::size_t i(0); i != std::ctype<char>::table_size; ++i) {
table[i] = tab[i] & ~std::ctype_base::space;
}
std::for_each(spaces.begin(), spaces.end(), [=](unsigned char c) {
table[c] |= std::ctype_base::space;
});
}
};
class whitespace_facet
: private whitespace_mask
, public std::ctype<char> {
public:
whitespace_facet(std::string const& spaces)
: whitespace_mask(spaces)
, std::ctype<char>(this->mask_table) {
}
};
struct whitespace {
std::string spaces;
whitespace(std::string const& spaces): spaces(spaces) {}
};
std::istream& operator>>(std::istream& in, whitespace const& ws) {
std::locale loc(in.getloc(), new whitespace_facet(ws.spaces));
in.imbue(loc);
return in;
}
// everything above would probably go into a utility library...
int main() {
std::istringstream in("a, b, c, d, e");
std::copy(std::istream_iterator<std::string>(in >> whitespace(", ")),
std::istream_iterator<std::string>(),
std::ostream_iterator<std::string>(std::cout, "\n"));
std::istringstream pipes("a b c| d |e e");
std::copy(std::istream_iterator<std::string>(pipes >> whitespace("|")),
std::istream_iterator<std::string>(),
std::ostream_iterator<std::string>(std::cout, "\n"));
}
大部分代码用于打包提供软分隔符的通用工具：合并一行中的多个分隔符。无法生成空序列。当流中需要不同的分隔符时，您可能会使用共享流缓冲区使用不同的设置流：
void f(std::istream& in) {
std::istream pipes(in.rdbuf());
pipes >> whitespace("|");
std::istream comma(in.rdbuf());
comma >> whitespace(",");
std::string s0, s1;
if (pipes >> s0 >> std::ws // read up to first pipe and ignore sequence of pipes
&& comma >> s1 >> std::ws) { // read up to first comma and ignore commas
// ...
}
}
其他回答
我对string和u32string~的一般实现，使用boost:：algorithm：：split签名。
template<typename CharT, typename UnaryPredicate>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
UnaryPredicate predicate)
{
using ST = std::basic_string<CharT>;
using std::swap;
std::vector<ST> tmp_result;
auto iter = s.cbegin(),
end_iter = s.cend();
while (true)
{
/**
* edge case: empty str -> push an empty str and exit.
*/
auto find_iter = find_if(iter, end_iter, predicate);
tmp_result.emplace_back(iter, find_iter);
if (find_iter == end_iter) { break; }
iter = ++find_iter;
}
swap(tmp_result, split_result);
}
template<typename CharT>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
const std::basic_string<CharT>& char_candidate)
{
std::unordered_set<CharT> candidate_set(char_candidate.cbegin(),
char_candidate.cend());
auto predicate = [&candidate_set](const CharT& c) {
return candidate_set.count(c) > 0U;
};
return split(split_result, s, predicate);
}
template<typename CharT>
void split(std::vector<std::basic_string<CharT>>& split_result,
const std::basic_string<CharT>& s,
const CharT* literals)
{
return split(split_result, s, std::basic_string<CharT>(literals));
}
使用std:：string_view和Eric Niebler的range-v3库：
https://wandbox.org/permlink/kW5lwRCL1pxjp2pW
#include <iostream>
#include <string>
#include <string_view>
#include "range/v3/view.hpp"
#include "range/v3/algorithm.hpp"
int main() {
std::string s = "Somewhere down the range v3 library";
ranges::for_each(s
| ranges::view::split(' ')
| ranges::view::transform([](auto &&sub) {
return std::string_view(&*sub.begin(), ranges::distance(sub));
}),
[](auto s) {std::cout << "Substring: " << s << "\n";}
);
}
通过使用循环的范围而不是范围：：for_each算法：
#include <iostream>
#include <string>
#include <string_view>
#include "range/v3/view.hpp"
int main()
{
std::string str = "Somewhere down the range v3 library";
for (auto s : str | ranges::view::split(' ')
| ranges::view::transform([](auto&& sub) { return std::string_view(&*sub.begin(), ranges::distance(sub)); }
))
{
std::cout << "Substring: " << s << "\n";
}
}
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;
}
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);
}
对于一个大得离谱而且可能是冗余的版本，可以尝试很多For循环。
string stringlist[10];
int count = 0;
for (int i = 0; i < sequence.length(); i++)
{
if (sequence[i] == ' ')
{
stringlist[count] = sequence.substr(0, i);
sequence.erase(0, i+1);
i = 0;
count++;
}
else if (i == sequence.length()-1) // Last word
{
stringlist[count] = sequence.substr(0, i+1);
}
}
它并不漂亮，但总的来说（除了标点符号和一系列其他错误）它是有效的！
