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
我使用以下代码：
namespace Core
{
typedef std::wstring String;
void SplitString(const Core::String& input, const Core::String& splitter, std::list<Core::String>& output)
{
if (splitter.empty())
{
throw std::invalid_argument(); // for example
}
std::list<Core::String> lines;
Core::String::size_type offset = 0;
for (;;)
{
Core::String::size_type splitterPos = input.find(splitter, offset);
if (splitterPos != Core::String::npos)
{
lines.push_back(input.substr(offset, splitterPos - offset));
offset = splitterPos + splitter.size();
}
else
{
lines.push_back(input.substr(offset));
break;
}
}
lines.swap(output);
}
}
// gtest:
class SplitStringTest: public testing::Test
{
};
TEST_F(SplitStringTest, EmptyStringAndSplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(Core::String(), Core::String(), result));
}
TEST_F(SplitStringTest, NonEmptyStringAndEmptySplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(L"xy", Core::String(), result));
}
TEST_F(SplitStringTest, EmptyStringAndNonEmptySplitter)
{
std::list<Core::String> result;
Core::SplitString(Core::String(), Core::String(L","), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(Core::String(), *result.begin());
}
TEST_F(SplitStringTest, OneCharSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,y", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
Core::SplitString(L",xy", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L"xy", *result.rbegin());
Core::SplitString(L"xy,", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"xy", *result.begin());
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, TwoCharsSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,.y,z", L",.", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
Core::SplitString(L"x,,y,z", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
}
TEST_F(SplitStringTest, RecursiveSplitter)
{
std::list<Core::String> result;
Core::SplitString(L",,,", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L",", *result.rbegin());
Core::SplitString(L",.,.,", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L".,", *result.rbegin());
Core::SplitString(L"x,.,.,y", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L".,y", *result.rbegin());
Core::SplitString(L",.,,.,", L",.,", result);
ASSERT_EQ(3, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(Core::String(), *(++result.begin()));
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, NullTerminators)
{
std::list<Core::String> result;
Core::SplitString(L"xy", Core::String(L"\0", 1), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(L"xy", *result.begin());
Core::SplitString(Core::String(L"x\0y", 3), Core::String(L"\0", 1), result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
}
其他回答
C++20终于为我们提供了一个分裂函数。或者更确切地说，是一个范围适配器。螺栓连杆。
#include <iostream>
#include <ranges>
#include <string_view>
namespace ranges = std::ranges;
namespace views = std::views;
using str = std::string_view;
constexpr auto view =
"Multiple words"
| views::split(' ')
| views::transform([](auto &&r) -> str {
return {
&*r.begin(),
static_cast<str::size_type>(ranges::distance(r))
};
});
auto main() -> int {
for (str &&sv : view) {
std::cout << sv << '\n';
}
}
没有任何内存分配的C++17版本（std:：函数除外）
void iter_words(const std::string_view& input, const std::function<void(std::string_view)>& process_word) {
auto itr = input.begin();
auto consume_whitespace = [&]() {
for(; itr != input.end(); ++itr) {
if(!isspace(*itr))
return;
}
};
auto consume_letters = [&]() {
for(; itr != input.end(); ++itr) {
if(isspace(*itr))
return;
}
};
while(true) {
consume_whitespace();
if(itr == input.end())
return;
auto word_start = itr - input.begin();
consume_letters();
auto word_end = itr - input.begin();
process_word(input.substr(word_start, word_end - word_start));
}
}
int main() {
iter_words("foo bar", [](std::string_view sv) {
std::cout << "Got word: " << sv << '\n';
});
return 0;
}
谢谢@Jairo Abdiel Toribio Cisneros。它对我有效，但您的函数返回一些空元素。因此，对于没有空的返回，我编辑了以下内容：
std::vector<std::string> split(std::string str, const char* delim) {
std::vector<std::string> v;
std::string tmp;
for(std::string::const_iterator i = str.begin(); i <= str.end(); ++i) {
if(*i != *delim && i != str.end()) {
tmp += *i;
} else {
if (tmp.length() > 0) {
v.push_back(tmp);
}
tmp = "";
}
}
return v;
}
使用：
std::string s = "one:two::three";
std::string delim = ":";
std::vector<std::string> vv = split(s, delim.c_str());
我一直在寻找用任意长度的分隔符分割字符串的方法，所以我开始从头开始编写，因为现有的解决方案不适合我。
这是我的小算法，仅使用STL：
//use like this
//std::vector<std::wstring> vec = Split<std::wstring> (L"Hello##world##!", L"##");
template <typename valueType>
static std::vector <valueType> Split (valueType text, const valueType& delimiter)
{
std::vector <valueType> tokens;
size_t pos = 0;
valueType token;
while ((pos = text.find(delimiter)) != valueType::npos)
{
token = text.substr(0, pos);
tokens.push_back (token);
text.erase(0, pos + delimiter.length());
}
tokens.push_back (text);
return tokens;
}
根据我的测试，它可以与任何长度和形式的分隔符一起使用。使用string或wstring类型实例化。
该算法所做的就是搜索分隔符，获取字符串中与分隔符相邻的部分，删除分隔符，然后再次搜索，直到不再找到为止。
当然，可以使用任意数量的空格作为分隔符。
我希望这有帮助。
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";
}
}
