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
这里有一个只使用标准正则表达式库的简单解决方案
#include <regex>
#include <string>
#include <vector>
std::vector<string> Tokenize( const string str, const std::regex regex )
{
using namespace std;
std::vector<string> result;
sregex_token_iterator it( str.begin(), str.end(), regex, -1 );
sregex_token_iterator reg_end;
for ( ; it != reg_end; ++it ) {
if ( !it->str().empty() ) //token could be empty:check
result.emplace_back( it->str() );
}
return result;
}
正则表达式参数允许检查多个参数（空格、逗号等）
我通常只选中空格和逗号分隔，所以我也有这个默认函数：
std::vector<string> TokenizeDefault( const string str )
{
using namespace std;
regex re( "[\\s,]+" );
return Tokenize( str, re );
}
“[\\s，]+”检查空格（\\s）和逗号（，）。
注意，如果要拆分wstring而不是string，
将所有std:：regex更改为std:：wregex将所有sregex_token_iterator更改为wsregex_token_idterator
注意，根据编译器的不同，您可能还希望引用字符串参数。
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。
下面的代码使用strtok（）将字符串拆分为标记，并将标记存储在向量中。
#include <iostream>
#include <algorithm>
#include <vector>
#include <string>
using namespace std;
char one_line_string[] = "hello hi how are you nice weather we are having ok then bye";
char seps[] = " ,\t\n";
char *token;
int main()
{
vector<string> vec_String_Lines;
token = strtok( one_line_string, seps );
cout << "Extracting and storing data in a vector..\n\n\n";
while( token != NULL )
{
vec_String_Lines.push_back(token);
token = strtok( NULL, seps );
}
cout << "Displaying end result in vector line storage..\n\n";
for ( int i = 0; i < vec_String_Lines.size(); ++i)
cout << vec_String_Lines[i] << "\n";
cout << "\n\n\n";
return 0;
}
我使用以下代码：
namespace Core
{
typedef std::wstring String;
void SplitString(const Core::String& input, const Core::String& splitter, std::list<Core::String>& output)
{
if (splitter.empty())
{
throw std::invalid_argument(); // for example
}
std::list<Core::String> lines;
Core::String::size_type offset = 0;
for (;;)
{
Core::String::size_type splitterPos = input.find(splitter, offset);
if (splitterPos != Core::String::npos)
{
lines.push_back(input.substr(offset, splitterPos - offset));
offset = splitterPos + splitter.size();
}
else
{
lines.push_back(input.substr(offset));
break;
}
}
lines.swap(output);
}
}
// gtest:
class SplitStringTest: public testing::Test
{
};
TEST_F(SplitStringTest, EmptyStringAndSplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(Core::String(), Core::String(), result));
}
TEST_F(SplitStringTest, NonEmptyStringAndEmptySplitter)
{
std::list<Core::String> result;
ASSERT_ANY_THROW(Core::SplitString(L"xy", Core::String(), result));
}
TEST_F(SplitStringTest, EmptyStringAndNonEmptySplitter)
{
std::list<Core::String> result;
Core::SplitString(Core::String(), Core::String(L","), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(Core::String(), *result.begin());
}
TEST_F(SplitStringTest, OneCharSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,y", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
Core::SplitString(L",xy", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L"xy", *result.rbegin());
Core::SplitString(L"xy,", L",", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"xy", *result.begin());
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, TwoCharsSplitter)
{
std::list<Core::String> result;
Core::SplitString(L"x,.y,z", L",.", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
Core::SplitString(L"x,,y,z", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y,z", *result.rbegin());
}
TEST_F(SplitStringTest, RecursiveSplitter)
{
std::list<Core::String> result;
Core::SplitString(L",,,", L",,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L",", *result.rbegin());
Core::SplitString(L",.,.,", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(L".,", *result.rbegin());
Core::SplitString(L"x,.,.,y", L",.,", result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L".,y", *result.rbegin());
Core::SplitString(L",.,,.,", L",.,", result);
ASSERT_EQ(3, result.size());
ASSERT_EQ(Core::String(), *result.begin());
ASSERT_EQ(Core::String(), *(++result.begin()));
ASSERT_EQ(Core::String(), *result.rbegin());
}
TEST_F(SplitStringTest, NullTerminators)
{
std::list<Core::String> result;
Core::SplitString(L"xy", Core::String(L"\0", 1), result);
ASSERT_EQ(1, result.size());
ASSERT_EQ(L"xy", *result.begin());
Core::SplitString(Core::String(L"x\0y", 3), Core::String(L"\0", 1), result);
ASSERT_EQ(2, result.size());
ASSERT_EQ(L"x", *result.begin());
ASSERT_EQ(L"y", *result.rbegin());
}
在处理空格作为分隔符时，使用std:：istream_iterator<T>的明显答案已经给出，并得到了很多支持。当然，元素可能不是用空格分隔，而是用一些分隔符分隔。我没有找到任何答案，只是重新定义了空格的含义，将其称为分隔符，然后使用常规方法。
要改变流对空白的看法，只需使用（std:：istream:：imbue（））将流的std:：locale更改为std:：ctype<char>方面，并定义空白的含义（也可以对std:：：ctype<wchar_t>进行更改，但实际上略有不同，因为std:：actype<char>是表驱动的，而std:：type<wchar_t>是由虚拟函数驱动的）。
#include <iostream>
#include <algorithm>
#include <iterator>
#include <sstream>
#include <locale>
struct whitespace_mask {
std::ctype_base::mask mask_table[std::ctype<char>::table_size];
whitespace_mask(std::string const& spaces) {
std::ctype_base::mask* table = this->mask_table;
std::ctype_base::mask const* tab
= std::use_facet<std::ctype<char>>(std::locale()).table();
for (std::size_t i(0); i != std::ctype<char>::table_size; ++i) {
table[i] = tab[i] & ~std::ctype_base::space;
}
std::for_each(spaces.begin(), spaces.end(), [=](unsigned char c) {
table[c] |= std::ctype_base::space;
});
}
};
class whitespace_facet
: private whitespace_mask
, public std::ctype<char> {
public:
whitespace_facet(std::string const& spaces)
: whitespace_mask(spaces)
, std::ctype<char>(this->mask_table) {
}
};
struct whitespace {
std::string spaces;
whitespace(std::string const& spaces): spaces(spaces) {}
};
std::istream& operator>>(std::istream& in, whitespace const& ws) {
std::locale loc(in.getloc(), new whitespace_facet(ws.spaces));
in.imbue(loc);
return in;
}
// everything above would probably go into a utility library...
int main() {
std::istringstream in("a, b, c, d, e");
std::copy(std::istream_iterator<std::string>(in >> whitespace(", ")),
std::istream_iterator<std::string>(),
std::ostream_iterator<std::string>(std::cout, "\n"));
std::istringstream pipes("a b c| d |e e");
std::copy(std::istream_iterator<std::string>(pipes >> whitespace("|")),
std::istream_iterator<std::string>(),
std::ostream_iterator<std::string>(std::cout, "\n"));
}
大部分代码用于打包提供软分隔符的通用工具：合并一行中的多个分隔符。无法生成空序列。当流中需要不同的分隔符时，您可能会使用共享流缓冲区使用不同的设置流：
void f(std::istream& in) {
std::istream pipes(in.rdbuf());
pipes >> whitespace("|");
std::istream comma(in.rdbuf());
comma >> whitespace(",");
std::string s0, s1;
if (pipes >> s0 >> std::ws // read up to first pipe and ignore sequence of pipes
&& comma >> s1 >> std::ws) { // read up to first comma and ignore commas
// ...
}
}
每个人都回答了预定义的字符串输入。我认为这个答案将帮助某人进行扫描输入。
我使用令牌向量来保存字符串令牌。这是可选的。
#include <bits/stdc++.h>
using namespace std ;
int main()
{
string str, token ;
getline(cin, str) ; // get the string as input
istringstream ss(str); // insert the string into tokenizer
vector<string> tokens; // vector tokens holds the tokens
while (ss >> token) tokens.push_back(token); // splits the tokens
for(auto x : tokens) cout << x << endl ; // prints the tokens
return 0;
}
样本输入：
port city international university
样本输出：
port
city
international
university
注意，默认情况下，这将仅适用于空格作为分隔符。您可以使用自定义分隔符。为此，您定制了代码。让分隔符为“，”。所以使用
char delimiter = ',' ;
while(getline(ss, token, delimiter)) tokens.push_back(token) ;
而不是
while (ss >> token) tokens.push_back(token);
