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
还有另一种方式——连续传递方式、零分配、基于函数的分隔。
void split( auto&& data, auto&& splitter, auto&& operation ) {
using std::begin; using std::end;
auto prev = begin(data);
while (prev != end(data) ) {
auto&&[prev,next] = splitter( prev, end(data) );
operation(prev,next);
prev = next;
}
}
现在我们可以基于此编写特定的拆分函数。
auto anyOfSplitter(auto delimiters) {
return [delimiters](auto begin, auto end) {
while( begin != end && 0 == std::string_view(begin, end).find_first_of(delimiters) ) {
++begin;
}
auto view = std::string_view(begin, end);
auto next = view.find_first_of(delimiters);
if (next != view.npos)
return std::make_pair( begin, begin + next );
else
return std::make_pair( begin, end );
};
}
我们现在可以生成一个传统的std字符串分割，如下所示：
template<class C>
auto traditional_any_of_split( std::string_view<C> str, std::string_view<C> delim ) {
std::vector<std::basic_string<C>> retval;
split( str, anyOfSplitter(delim), [&](auto s, auto f) {
retval.emplace_back(s,f);
});
return retval;
}
或者我们可以改用find
auto findSplitter(auto delimiter) {
return [delimiter](auto begin, auto end) {
while( begin != end && 0 == std::string_view(begin, end).find(delimiter) ) {
begin += delimiter.size();
}
auto view = std::string_view(begin, end);
auto next = view.find(delimiter);
if (next != view.npos)
return std::make_pair( begin, begin + next );
else
return std::make_pair( begin, end );
};
}
template<class C>
auto traditional_find_split( std::string_view<C> str, std::string_view<C> delim ) {
std::vector<std::basic_string<C>> retval;
split( str, findSplitter(delim), [&](auto s, auto f) {
retval.emplace_back(s,f);
});
return retval;
}
通过更换分流器部分。
这两者都分配了一个返回值缓冲区。我们可以以手动管理生命周期为代价将返回值交换到字符串视图。
我们还可以采用一个延续，一次传递一个字符串视图，甚至避免分配视图向量。
这可以通过一个中止选项进行扩展，这样我们可以在读取几个前缀字符串后中止。
其他回答
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());
}
我们可以在c++中使用strtok，
#include <iostream>
#include <cstring>
using namespace std;
int main()
{
char str[]="Mickey M;12034;911416313;M;01a;9001;NULL;0;13;12;0;CPP,C;MSC,3D;FEND,BEND,SEC;";
char *pch = strtok (str,";,");
while (pch != NULL)
{
cout<<pch<<"\n";
pch = strtok (NULL, ";,");
}
return 0;
}
使用vector作为基类的快速版本，可完全访问其所有运算符：
// Split string into parts.
class Split : public std::vector<std::string>
{
public:
Split(const std::string& str, char* delimList)
{
size_t lastPos = 0;
size_t pos = str.find_first_of(delimList);
while (pos != std::string::npos)
{
if (pos != lastPos)
push_back(str.substr(lastPos, pos-lastPos));
lastPos = pos + 1;
pos = str.find_first_of(delimList, lastPos);
}
if (lastPos < str.length())
push_back(str.substr(lastPos, pos-lastPos));
}
};
用于填充STL集的示例：
std::set<std::string> words;
Split split("Hello,World", ",");
words.insert(split.begin(), split.end());
我用这个分隔符分隔字符串。第一个将结果放入预先构建的向量中，第二个返回新向量。
#include <string>
#include <sstream>
#include <vector>
#include <iterator>
template <typename Out>
void split(const std::string &s, char delim, Out result) {
std::istringstream iss(s);
std::string item;
while (std::getline(iss, item, delim)) {
*result++ = item;
}
}
std::vector<std::string> split(const std::string &s, char delim) {
std::vector<std::string> elems;
split(s, delim, std::back_inserter(elems));
return elems;
}
请注意，此解决方案不会跳过空令牌，因此下面将找到4项，其中一项为空：
std::vector<std::string> x = split("one:two::three", ':');
我编写了以下代码。您可以指定分隔符，它可以是字符串。结果类似于Java的String.split，结果中包含空字符串。
例如，如果我们调用split（“ABCPICKABCANYABCTWO:ABC”，“ABC”），结果如下：
0 <len:0>
1 PICK <len:4>
2 ANY <len:3>
3 TWO: <len:4>
4 <len:0>
代码：
vector <string> split(const string& str, const string& delimiter = " ") {
vector <string> tokens;
string::size_type lastPos = 0;
string::size_type pos = str.find(delimiter, lastPos);
while (string::npos != pos) {
// Found a token, add it to the vector.
cout << str.substr(lastPos, pos - lastPos) << endl;
tokens.push_back(str.substr(lastPos, pos - lastPos));
lastPos = pos + delimiter.size();
pos = str.find(delimiter, lastPos);
}
tokens.push_back(str.substr(lastPos, str.size() - lastPos));
return tokens;
}
