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
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;
}
其他回答
如果您喜欢使用boost，但希望使用整个字符串作为分隔符（而不是之前提出的大多数解决方案中的单个字符），可以使用boost_split_iterator。
示例代码包括方便的模板：
#include <iostream>
#include <vector>
#include <boost/algorithm/string.hpp>
template<typename _OutputIterator>
inline void split(
const std::string& str,
const std::string& delim,
_OutputIterator result)
{
using namespace boost::algorithm;
typedef split_iterator<std::string::const_iterator> It;
for(It iter=make_split_iterator(str, first_finder(delim, is_equal()));
iter!=It();
++iter)
{
*(result++) = boost::copy_range<std::string>(*iter);
}
}
int main(int argc, char* argv[])
{
using namespace std;
vector<string> splitted;
split("HelloFOOworldFOO!", "FOO", back_inserter(splitted));
// or directly to console, for example
split("HelloFOOworldFOO!", "FOO", ostream_iterator<string>(cout, "\n"));
return 0;
}
使用Boost的可能解决方案可能是：
#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));
这种方法可能比字符串流方法更快。由于这是一个通用模板函数，因此可以使用各种分隔符拆分其他类型的字符串（wchar等或UTF-8）。
有关详细信息，请参阅文档。
我的实施可以是另一种解决方案：
std::vector<std::wstring> SplitString(const std::wstring & String, const std::wstring & Seperator)
{
std::vector<std::wstring> Lines;
size_t stSearchPos = 0;
size_t stFoundPos;
while (stSearchPos < String.size() - 1)
{
stFoundPos = String.find(Seperator, stSearchPos);
stFoundPos = (stFoundPos == std::string::npos) ? String.size() : stFoundPos;
Lines.push_back(String.substr(stSearchPos, stFoundPos - stSearchPos));
stSearchPos = stFoundPos + Seperator.size();
}
return Lines;
}
测试代码：
std::wstring MyString(L"Part 1SEPsecond partSEPlast partSEPend");
std::vector<std::wstring> Parts = IniFile::SplitString(MyString, L"SEP");
std::wcout << L"The string: " << MyString << std::endl;
for (std::vector<std::wstring>::const_iterator it=Parts.begin(); it<Parts.end(); ++it)
{
std::wcout << *it << L"<---" << std::endl;
}
std::wcout << std::endl;
MyString = L"this,time,a,comma separated,string";
std::wcout << L"The string: " << MyString << std::endl;
Parts = IniFile::SplitString(MyString, L",");
for (std::vector<std::wstring>::const_iterator it=Parts.begin(); it<Parts.end(); ++it)
{
std::wcout << *it << L"<---" << std::endl;
}
测试代码的输出：
The string: Part 1SEPsecond partSEPlast partSEPend
Part 1<---
second part<---
last part<---
end<---
The string: this,time,a,comma separated,string
this<---
time<---
a<---
comma separated<---
string<---
这是一个顶级答案的扩展。它现在支持设置返回元素的最大数量N。字符串的最后一位将在第N个元素中结束。MAXELEMENTS参数是可选的，如果设置为默认值0，它将返回无限数量的元素。：-）
.h:
class Myneatclass {
public:
static std::vector<std::string>& split(const std::string &s, char delim, std::vector<std::string> &elems, const size_t MAXELEMENTS = 0);
static std::vector<std::string> split(const std::string &s, char delim, const size_t MAXELEMENTS = 0);
};
.cpp：
std::vector<std::string>& Myneatclass::split(const std::string &s, char delim, std::vector<std::string> &elems, const size_t MAXELEMENTS) {
std::stringstream ss(s);
std::string item;
while (std::getline(ss, item, delim)) {
elems.push_back(item);
if (MAXELEMENTS > 0 && !ss.eof() && elems.size() + 1 >= MAXELEMENTS) {
std::getline(ss, item);
elems.push_back(item);
break;
}
}
return elems;
}
std::vector<std::string> Myneatclass::split(const std::string &s, char delim, const size_t MAXELEMENTS) {
std::vector<std::string> elems;
split(s, delim, elems, MAXELEMENTS);
return elems;
}
下面是一个更好的方法。它可以接受任何字符，除非您愿意，否则不会拆分行。不需要特殊的库（嗯，除了std，但谁真的认为这是一个额外的库），没有指针，没有引用，而且它是静态的。只是简单的C++。
#pragma once
#include <vector>
#include <sstream>
using namespace std;
class Helpers
{
public:
static vector<string> split(string s, char delim)
{
stringstream temp (stringstream::in | stringstream::out);
vector<string> elems(0);
if (s.size() == 0 || delim == 0)
return elems;
for(char c : s)
{
if(c == delim)
{
elems.push_back(temp.str());
temp = stringstream(stringstream::in | stringstream::out);
}
else
temp << c;
}
if (temp.str().size() > 0)
elems.push_back(temp.str());
return elems;
}
//Splits string s with a list of delimiters in delims (it's just a list, like if we wanted to
//split at the following letters, a, b, c we would make delims="abc".
static vector<string> split(string s, string delims)
{
stringstream temp (stringstream::in | stringstream::out);
vector<string> elems(0);
bool found;
if(s.size() == 0 || delims.size() == 0)
return elems;
for(char c : s)
{
found = false;
for(char d : delims)
{
if (c == d)
{
elems.push_back(temp.str());
temp = stringstream(stringstream::in | stringstream::out);
found = true;
break;
}
}
if(!found)
temp << c;
}
if(temp.str().size() > 0)
elems.push_back(temp.str());
return elems;
}
};
