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
这是我的版本
#include <vector>
inline std::vector<std::string> Split(const std::string &str, const std::string &delim = " ")
{
std::vector<std::string> tokens;
if (str.size() > 0)
{
if (delim.size() > 0)
{
std::string::size_type currPos = 0, prevPos = 0;
while ((currPos = str.find(delim, prevPos)) != std::string::npos)
{
std::string item = str.substr(prevPos, currPos - prevPos);
if (item.size() > 0)
{
tokens.push_back(item);
}
prevPos = currPos + 1;
}
tokens.push_back(str.substr(prevPos));
}
else
{
tokens.push_back(str);
}
}
return tokens;
}
它适用于多字符分隔符。它防止空令牌进入结果。它使用单个标头。当您不提供分隔符时，它将字符串作为一个标记返回。如果字符串为空，它还会返回一个空结果。不幸的是，它的效率很低，因为存在巨大的std:：vector副本，除非您使用C++11进行编译，否则应该使用移动示意图。在C++11中，这段代码应该很快。
其他回答
值得一提的是，这里有另一种从输入字符串中提取令牌的方法，仅依赖于标准库设施。这是STL设计背后力量和优雅的一个例子。
#include <iostream>
#include <string>
#include <sstream>
#include <algorithm>
#include <iterator>
int main() {
using namespace std;
string sentence = "And I feel fine...";
istringstream iss(sentence);
copy(istream_iterator<string>(iss),
istream_iterator<string>(),
ostream_iterator<string>(cout, "\n"));
}
可以使用相同的通用复制算法将提取的令牌插入到容器中，而不是将其复制到输出流中。
vector<string> tokens;
copy(istream_iterator<string>(iss),
istream_iterator<string>(),
back_inserter(tokens));
…或直接创建矢量：
vector<string> tokens{istream_iterator<string>{iss},
istream_iterator<string>{}};
#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;
}
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());
}
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';
}
}
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);
}
