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
LazyString拆分器：
#include <string>
#include <algorithm>
#include <unordered_set>
using namespace std;
class LazyStringSplitter
{
string::const_iterator start, finish;
unordered_set<char> chop;
public:
// Empty Constructor
explicit LazyStringSplitter()
{}
explicit LazyStringSplitter (const string cstr, const string delims)
: start(cstr.begin())
, finish(cstr.end())
, chop(delims.begin(), delims.end())
{}
void operator () (const string cstr, const string delims)
{
chop.insert(delims.begin(), delims.end());
start = cstr.begin();
finish = cstr.end();
}
bool empty() const { return (start >= finish); }
string next()
{
// return empty string
// if ran out of characters
if (empty())
return string("");
auto runner = find_if(start, finish, [&](char c) {
return chop.count(c) == 1;
});
// construct next string
string ret(start, runner);
start = runner + 1;
// Never return empty string
// + tail recursion makes this method efficient
return !ret.empty() ? ret : next();
}
};
我将此方法称为LazyStringSplitter是因为一个原因——它不会一次性拆分字符串。本质上，它的行为类似于python生成器它公开了一个名为next的方法，该方法返回从原始字符串拆分的下一个字符串我使用了c++11STL中的无序集，因此查找分隔符的速度要快得多下面是它的工作原理
测试程序
#include <iostream>
using namespace std;
int main()
{
LazyStringSplitter splitter;
// split at the characters ' ', '!', '.', ','
splitter("This, is a string. And here is another string! Let's test and see how well this does.", " !.,");
while (!splitter.empty())
cout << splitter.next() << endl;
return 0;
}
输出，输出
This
is
a
string
And
here
is
another
string
Let's
test
and
see
how
well
this
does
改进这一点的下一个计划是实施开始和结束方法，以便可以执行以下操作：
vector<string> split_string(splitter.begin(), splitter.end());
其他回答
在getline上以“”作为标记进行循环。
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；）
这是我写的一个函数，帮助我做了很多事情。它在为WebSocket做协议时帮助了我。
using namespace std;
#include <iostream>
#include <vector>
#include <sstream>
#include <string>
vector<string> split ( string input , string split_id ) {
vector<string> result;
int i = 0;
bool add;
string temp;
stringstream ss;
size_t found;
string real;
int r = 0;
while ( i != input.length() ) {
add = false;
ss << input.at(i);
temp = ss.str();
found = temp.find(split_id);
if ( found != string::npos ) {
add = true;
real.append ( temp , 0 , found );
} else if ( r > 0 && ( i+1 ) == input.length() ) {
add = true;
real.append ( temp , 0 , found );
}
if ( add ) {
result.push_back(real);
ss.str(string());
ss.clear();
temp.clear();
real.clear();
r = 0;
}
i++;
r++;
}
return result;
}
int main() {
string s = "S,o,m,e,w,h,e,r,e, down the road \n In a really big C++ house. \n Lives a little old lady. \n That no one ever knew. \n She comes outside. \n In the very hot sun. \n\n\n\n\n\n\n\n And throws C++ at us. \n The End. FIN.";
vector < string > Token;
Token = split ( s , "," );
for ( int i = 0 ; i < Token.size(); i++) cout << Token.at(i) << endl;
cout << endl << Token.size();
int a;
cin >> a;
return a;
}
STL还没有这样的方法。
但是，您可以通过使用std:：string:：C_str（）成员来使用C的strtok（）函数，也可以编写自己的函数。下面是我在快速谷歌搜索（“STL字符串分割”）后找到的代码示例：
void Tokenize(const string& str,
vector<string>& tokens,
const string& delimiters = " ")
{
// Skip delimiters at beginning.
string::size_type lastPos = str.find_first_not_of(delimiters, 0);
// Find first "non-delimiter".
string::size_type pos = str.find_first_of(delimiters, lastPos);
while (string::npos != pos || string::npos != lastPos)
{
// Found a token, add it to the vector.
tokens.push_back(str.substr(lastPos, pos - lastPos));
// Skip delimiters. Note the "not_of"
lastPos = str.find_first_not_of(delimiters, pos);
// Find next "non-delimiter"
pos = str.find_first_of(delimiters, lastPos);
}
}
摘自：http://oopweb.com/CPP/Documents/CPPHOWTO/Volume/C++编程-HOWTO-7.html
如果您对代码示例有疑问，请留下评论，我会解释。
仅仅因为它没有实现称为迭代器的typedef或重载<<运算符，并不意味着它是错误的代码。我经常使用C函数。例如，printf和scanf都比std:：cin和std:：cout快（很明显），fopen语法对二进制类型更友好，它们也倾向于生成更小的EXE。
不要被这种“优雅胜过性能”的交易所吸引。
我刚刚写了一个很好的例子，说明如何按符号拆分一个字符，然后将每个字符数组（由符号分隔的单词）放入一个向量中。为了简单起见，我创建了std字符串的向量类型。
我希望这对你有帮助，并且对你可读。
#include <vector>
#include <string>
#include <iostream>
void push(std::vector<std::string> &WORDS, std::string &TMP){
WORDS.push_back(TMP);
TMP = "";
}
std::vector<std::string> mySplit(char STRING[]){
std::vector<std::string> words;
std::string s;
for(unsigned short i = 0; i < strlen(STRING); i++){
if(STRING[i] != ' '){
s += STRING[i];
}else{
push(words, s);
}
}
push(words, s);//Used to get last split
return words;
}
int main(){
char string[] = "My awesome string.";
std::cout << mySplit(string)[2];
std::cin.get();
return 0;
}
