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;
}
其他回答
对于那个些需要使用字符串分隔符拆分字符串的人，也许可以尝试我的以下解决方案。
std::vector<size_t> str_pos(const std::string &search, const std::string &target)
{
std::vector<size_t> founds;
if(!search.empty())
{
size_t start_pos = 0;
while (true)
{
size_t found_pos = target.find(search, start_pos);
if(found_pos != std::string::npos)
{
size_t found = found_pos;
founds.push_back(found);
start_pos = (found_pos + 1);
}
else
{
break;
}
}
}
return founds;
}
std::string str_sub_index(size_t begin_index, size_t end_index, const std::string &target)
{
std::string sub;
size_t size = target.length();
const char* copy = target.c_str();
for(size_t i = begin_index; i <= end_index; i++)
{
if(i >= size)
{
break;
}
else
{
char c = copy[i];
sub += c;
}
}
return sub;
}
std::vector<std::string> str_split(const std::string &delimiter, const std::string &target)
{
std::vector<std::string> splits;
if(!delimiter.empty())
{
std::vector<size_t> founds = str_pos(delimiter, target);
size_t founds_size = founds.size();
if(founds_size > 0)
{
size_t search_len = delimiter.length();
size_t begin_index = 0;
for(int i = 0; i <= founds_size; i++)
{
std::string sub;
if(i != founds_size)
{
size_t pos = founds.at(i);
sub = str_sub_index(begin_index, pos - 1, target);
begin_index = (pos + search_len);
}
else
{
sub = str_sub_index(begin_index, (target.length() - 1), target);
}
splits.push_back(sub);
}
}
}
return splits;
}
这些片段由3个函数组成。坏消息是使用str_split函数，您将需要另外两个函数。是的，这是一大块代码。但好消息是，这两个附加功能可以独立工作，有时也很有用
测试main（）块中的函数如下：
int main()
{
std::string s = "Hello, world! We need to make the world a better place. Because your world is also my world, and our children's world.";
std::vector<std::string> split = str_split("world", s);
for(int i = 0; i < split.size(); i++)
{
std::cout << split[i] << std::endl;
}
}
它将产生：
Hello,
! We need to make the
a better place. Because your
is also my
, and our children's
.
我认为这不是最有效的代码，但至少它可以工作。希望有帮助。
有一种更简单的方法可以做到这一点！！
#include <vector>
#include <string>
std::vector<std::string> splitby(std::string string, char splitter) {
int splits = 0;
std::vector<std::string> result = {};
std::string locresult = "";
for (unsigned int i = 0; i < string.size(); i++) {
if ((char)string.at(i) != splitter) {
locresult += string.at(i);
}
else {
result.push_back(locresult);
locresult = "";
}
}
if (splits == 0) {
result.push_back(locresult);
}
return result;
}
void printvector(std::vector<std::string> v) {
std::cout << '{';
for (unsigned int i = 0; i < v.size(); i++) {
if (i < v.size() - 1) {
std::cout << '"' << v.at(i) << "\",";
}
else {
std::cout << '"' << v.at(i) << "\"";
}
}
std::cout << "}\n";
}
我已经使用strtok滚动了自己的代码，并使用boost拆分了一个字符串。我找到的最好的方法是C++字符串工具包库。它非常灵活和快速。
#include <iostream>
#include <vector>
#include <string>
#include <strtk.hpp>
const char *whitespace = " \t\r\n\f";
const char *whitespace_and_punctuation = " \t\r\n\f;,=";
int main()
{
{ // normal parsing of a string into a vector of strings
std::string s("Somewhere down the road");
std::vector<std::string> result;
if( strtk::parse( s, whitespace, result ) )
{
for(size_t i = 0; i < result.size(); ++i )
std::cout << result[i] << std::endl;
}
}
{ // parsing a string into a vector of floats with other separators
// besides spaces
std::string s("3.0, 3.14; 4.0");
std::vector<float> values;
if( strtk::parse( s, whitespace_and_punctuation, values ) )
{
for(size_t i = 0; i < values.size(); ++i )
std::cout << values[i] << std::endl;
}
}
{ // parsing a string into specific variables
std::string s("angle = 45; radius = 9.9");
std::string w1, w2;
float v1, v2;
if( strtk::parse( s, whitespace_and_punctuation, w1, v1, w2, v2) )
{
std::cout << "word " << w1 << ", value " << v1 << std::endl;
std::cout << "word " << w2 << ", value " << v2 << std::endl;
}
}
return 0;
}
该工具包比这个简单示例显示的灵活性要高得多，但它在将字符串解析为有用元素方面的实用性令人难以置信。
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());
这是我的方法，切割和分割：
string cut (string& str, const string& del)
{
string f = str;
if (in.find_first_of(del) != string::npos)
{
f = str.substr(0,str.find_first_of(del));
str = str.substr(str.find_first_of(del)+del.length());
}
return f;
}
vector<string> split (const string& in, const string& del=" ")
{
vector<string> out();
string t = in;
while (t.length() > del.length())
out.push_back(cut(t,del));
return out;
}
顺便说一下，如果我能做些什么来优化这个。。
