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
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());
这里有一个仅使用标准正则表达式库的正则表达式解决方案。（我有点生疏，所以可能会有一些语法错误，但这至少是一般的想法）
#include <regex.h>
#include <string.h>
#include <vector.h>
using namespace std;
vector<string> split(string s){
regex r ("\\w+"); //regex matches whole words, (greedy, so no fragment words)
regex_iterator<string::iterator> rit ( s.begin(), s.end(), r );
regex_iterator<string::iterator> rend; //iterators to iterate thru words
vector<string> result<regex_iterator>(rit, rend);
return result; //iterates through the matches to fill the vector
}
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<---
这是我最喜欢的遍历字符串的方法。每个词你都可以做你想做的事。
string line = "a line of text to iterate through";
string word;
istringstream iss(line, istringstream::in);
while( iss >> word )
{
// Do something on `word` here...
}
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;
}
};
