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));
}
其他回答
到目前为止，我在Boost中使用了这个，但我需要一些不依赖它的东西，所以我得出了这个结论：
static void Split(std::vector<std::string>& lst, const std::string& input, const std::string& separators, bool remove_empty = true)
{
std::ostringstream word;
for (size_t n = 0; n < input.size(); ++n)
{
if (std::string::npos == separators.find(input[n]))
word << input[n];
else
{
if (!word.str().empty() || !remove_empty)
lst.push_back(word.str());
word.str("");
}
}
if (!word.str().empty() || !remove_empty)
lst.push_back(word.str());
}
好的一点是，在分隔符中可以传递多个字符。
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）
有一个名为strtok的函数。
#include<string>
using namespace std;
vector<string> split(char* str,const char* delim)
{
char* saveptr;
char* token = strtok_r(str,delim,&saveptr);
vector<string> result;
while(token != NULL)
{
result.push_back(token);
token = strtok_r(NULL,delim,&saveptr);
}
return result;
}
我相信还没有人发布这个解决方案。与其直接使用分隔符，它基本上与boost:：split（）相同，即它允许您传递一个谓词，如果字符是分隔符，则返回true，否则返回false。我认为这给了程序员更多的控制，最棒的是你不需要提升。
template <class Container, class String, class Predicate>
void split(Container& output, const String& input,
const Predicate& pred, bool trimEmpty = false) {
auto it = begin(input);
auto itLast = it;
while (it = find_if(it, end(input), pred), it != end(input)) {
if (not (trimEmpty and it == itLast)) {
output.emplace_back(itLast, it);
}
++it;
itLast = it;
}
}
然后可以这样使用：
struct Delim {
bool operator()(char c) {
return not isalpha(c);
}
};
int main() {
string s("#include<iostream>\n"
"int main() { std::cout << \"Hello world!\" << std::endl; }");
vector<string> v;
split(v, s, Delim(), true);
/* Which is also the same as */
split(v, s, [](char c) { return not isalpha(c); }, true);
for (const auto& i : v) {
cout << i << endl;
}
}
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());
}
