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
仅为方便：
template<class V, typename T>
bool in(const V &v, const T &el) {
return std::find(v.begin(), v.end(), el) != v.end();
}
基于多个分隔符的实际拆分：
std::vector<std::string> split(const std::string &s,
const std::vector<char> &delims) {
std::vector<std::string> res;
auto stuff = [&delims](char c) { return !in(delims, c); };
auto space = [&delims](char c) { return in(delims, c); };
auto first = std::find_if(s.begin(), s.end(), stuff);
while (first != s.end()) {
auto last = std::find_if(first, s.end(), space);
res.push_back(std::string(first, last));
first = std::find_if(last + 1, s.end(), stuff);
}
return res;
}
用法：
int main() {
std::string s = " aaa, bb cc ";
for (auto el: split(s, {' ', ','}))
std::cout << el << std::endl;
return 0;
}
其他回答
另一种灵活快速的方式
template<typename Operator>
void tokenize(Operator& op, const char* input, const char* delimiters) {
const char* s = input;
const char* e = s;
while (*e != 0) {
e = s;
while (*e != 0 && strchr(delimiters, *e) == 0) ++e;
if (e - s > 0) {
op(s, e - s);
}
s = e + 1;
}
}
要将其与字符串向量一起使用（编辑：由于有人指出不继承STL类…hrmf；）：
template<class ContainerType>
class Appender {
public:
Appender(ContainerType& container) : container_(container) {;}
void operator() (const char* s, unsigned length) {
container_.push_back(std::string(s,length));
}
private:
ContainerType& container_;
};
std::vector<std::string> strVector;
Appender v(strVector);
tokenize(v, "A number of words to be tokenized", " \t");
就是这样！这只是使用tokenizer的一种方式，比如如何计数单词：
class WordCounter {
public:
WordCounter() : noOfWords(0) {}
void operator() (const char*, unsigned) {
++noOfWords;
}
unsigned noOfWords;
};
WordCounter wc;
tokenize(wc, "A number of words to be counted", " \t");
ASSERT( wc.noOfWords == 7 );
受限于想象力；）
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;
}
我的代码是：
#include <list>
#include <string>
template<class StringType = std::string, class ContainerType = std::list<StringType> >
class DSplitString:public ContainerType
{
public:
explicit DSplitString(const StringType& strString, char cChar, bool bSkipEmptyParts = true)
{
size_t iPos = 0;
size_t iPos_char = 0;
while(StringType::npos != (iPos_char = strString.find(cChar, iPos)))
{
StringType strTemp = strString.substr(iPos, iPos_char - iPos);
if((bSkipEmptyParts && !strTemp.empty()) || (!bSkipEmptyParts))
push_back(strTemp);
iPos = iPos_char + 1;
}
}
explicit DSplitString(const StringType& strString, const StringType& strSub, bool bSkipEmptyParts = true)
{
size_t iPos = 0;
size_t iPos_char = 0;
while(StringType::npos != (iPos_char = strString.find(strSub, iPos)))
{
StringType strTemp = strString.substr(iPos, iPos_char - iPos);
if((bSkipEmptyParts && !strTemp.empty()) || (!bSkipEmptyParts))
push_back(strTemp);
iPos = iPos_char + strSub.length();
}
}
};
例子：
#include <iostream>
#include <string>
int _tmain(int argc, _TCHAR* argv[])
{
DSplitString<> aa("doicanhden1;doicanhden2;doicanhden3;", ';');
for each (std::string var in aa)
{
std::cout << var << std::endl;
}
std::cin.get();
return 0;
}
作为一个业余爱好者，这是我想到的第一个解决方案。我有点好奇，为什么我还没有在这里看到类似的解决方案，是不是我的做法有根本问题？
#include <iostream>
#include <string>
#include <vector>
std::vector<std::string> split(const std::string &s, const std::string &delims)
{
std::vector<std::string> result;
std::string::size_type pos = 0;
while (std::string::npos != (pos = s.find_first_not_of(delims, pos))) {
auto pos2 = s.find_first_of(delims, pos);
result.emplace_back(s.substr(pos, std::string::npos == pos2 ? pos2 : pos2 - pos));
pos = pos2;
}
return result;
}
int main()
{
std::string text{"And then I said: \"I don't get it, why would you even do that!?\""};
std::string delims{" :;\".,?!"};
auto words = split(text, delims);
std::cout << "\nSentence:\n " << text << "\n\nWords:";
for (const auto &w : words) {
std::cout << "\n " << w;
}
return 0;
}
http://cpp.sh/7wmzy
使用std：：stringstream非常好，并且完全符合您的要求。如果您只是在寻找不同的方法，那么可以使用std:：find（）/std:：find_first_of（）和std:：string：：substr（）。
下面是一个示例：
#include <iostream>
#include <string>
int main()
{
std::string s("Somewhere down the road");
std::string::size_type prev_pos = 0, pos = 0;
while( (pos = s.find(' ', pos)) != std::string::npos )
{
std::string substring( s.substr(prev_pos, pos-prev_pos) );
std::cout << substring << '\n';
prev_pos = ++pos;
}
std::string substring( s.substr(prev_pos, pos-prev_pos) ); // Last word
std::cout << substring << '\n';
return 0;
}
