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
我这样做是因为我需要一种简单的方法来分割字符串和基于c的字符串。。。希望其他人也能发现它很有用。此外，它不依赖令牌，您可以使用字段作为分隔符，这是我需要的另一个键。
我相信可以做一些改进，以进一步提高其优雅度，请尽一切努力
StringSplitter.hpp：
#include <vector>
#include <iostream>
#include <string.h>
using namespace std;
class StringSplit
{
private:
void copy_fragment(char*, char*, char*);
void copy_fragment(char*, char*, char);
bool match_fragment(char*, char*, int);
int untilnextdelim(char*, char);
int untilnextdelim(char*, char*);
void assimilate(char*, char);
void assimilate(char*, char*);
bool string_contains(char*, char*);
long calc_string_size(char*);
void copy_string(char*, char*);
public:
vector<char*> split_cstr(char);
vector<char*> split_cstr(char*);
vector<string> split_string(char);
vector<string> split_string(char*);
char* String;
bool do_string;
bool keep_empty;
vector<char*> Container;
vector<string> ContainerS;
StringSplit(char * in)
{
String = in;
}
StringSplit(string in)
{
size_t len = calc_string_size((char*)in.c_str());
String = new char[len + 1];
memset(String, 0, len + 1);
copy_string(String, (char*)in.c_str());
do_string = true;
}
~StringSplit()
{
for (int i = 0; i < Container.size(); i++)
{
if (Container[i] != NULL)
{
delete[] Container[i];
}
}
if (do_string)
{
delete[] String;
}
}
};
StringSplitter.cpp：
#include <string.h>
#include <iostream>
#include <vector>
#include "StringSplit.hpp"
using namespace std;
void StringSplit::assimilate(char*src, char delim)
{
int until = untilnextdelim(src, delim);
if (until > 0)
{
char * temp = new char[until + 1];
memset(temp, 0, until + 1);
copy_fragment(temp, src, delim);
if (keep_empty || *temp != 0)
{
if (!do_string)
{
Container.push_back(temp);
}
else
{
string x = temp;
ContainerS.push_back(x);
}
}
else
{
delete[] temp;
}
}
}
void StringSplit::assimilate(char*src, char* delim)
{
int until = untilnextdelim(src, delim);
if (until > 0)
{
char * temp = new char[until + 1];
memset(temp, 0, until + 1);
copy_fragment(temp, src, delim);
if (keep_empty || *temp != 0)
{
if (!do_string)
{
Container.push_back(temp);
}
else
{
string x = temp;
ContainerS.push_back(x);
}
}
else
{
delete[] temp;
}
}
}
long StringSplit::calc_string_size(char* _in)
{
long i = 0;
while (*_in++)
{
i++;
}
return i;
}
bool StringSplit::string_contains(char* haystack, char* needle)
{
size_t len = calc_string_size(needle);
size_t lenh = calc_string_size(haystack);
while (lenh--)
{
if (match_fragment(haystack + lenh, needle, len))
{
return true;
}
}
return false;
}
bool StringSplit::match_fragment(char* _src, char* cmp, int len)
{
while (len--)
{
if (*(_src + len) != *(cmp + len))
{
return false;
}
}
return true;
}
int StringSplit::untilnextdelim(char* _in, char delim)
{
size_t len = calc_string_size(_in);
if (*_in == delim)
{
_in += 1;
return len - 1;
}
int c = 0;
while (*(_in + c) != delim && c < len)
{
c++;
}
return c;
}
int StringSplit::untilnextdelim(char* _in, char* delim)
{
int s = calc_string_size(delim);
int c = 1 + s;
if (!string_contains(_in, delim))
{
return calc_string_size(_in);
}
else if (match_fragment(_in, delim, s))
{
_in += s;
return calc_string_size(_in);
}
while (!match_fragment(_in + c, delim, s))
{
c++;
}
return c;
}
void StringSplit::copy_fragment(char* dest, char* src, char delim)
{
if (*src == delim)
{
src++;
}
int c = 0;
while (*(src + c) != delim && *(src + c))
{
*(dest + c) = *(src + c);
c++;
}
*(dest + c) = 0;
}
void StringSplit::copy_string(char* dest, char* src)
{
int i = 0;
while (*(src + i))
{
*(dest + i) = *(src + i);
i++;
}
}
void StringSplit::copy_fragment(char* dest, char* src, char* delim)
{
size_t len = calc_string_size(delim);
size_t lens = calc_string_size(src);
if (match_fragment(src, delim, len))
{
src += len;
lens -= len;
}
int c = 0;
while (!match_fragment(src + c, delim, len) && (c < lens))
{
*(dest + c) = *(src + c);
c++;
}
*(dest + c) = 0;
}
vector<char*> StringSplit::split_cstr(char Delimiter)
{
int i = 0;
while (*String)
{
if (*String != Delimiter && i == 0)
{
assimilate(String, Delimiter);
}
if (*String == Delimiter)
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return Container;
}
vector<string> StringSplit::split_string(char Delimiter)
{
do_string = true;
int i = 0;
while (*String)
{
if (*String != Delimiter && i == 0)
{
assimilate(String, Delimiter);
}
if (*String == Delimiter)
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return ContainerS;
}
vector<char*> StringSplit::split_cstr(char* Delimiter)
{
int i = 0;
size_t LenDelim = calc_string_size(Delimiter);
while(*String)
{
if (!match_fragment(String, Delimiter, LenDelim) && i == 0)
{
assimilate(String, Delimiter);
}
if (match_fragment(String, Delimiter, LenDelim))
{
assimilate(String,Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return Container;
}
vector<string> StringSplit::split_string(char* Delimiter)
{
do_string = true;
int i = 0;
size_t LenDelim = calc_string_size(Delimiter);
while (*String)
{
if (!match_fragment(String, Delimiter, LenDelim) && i == 0)
{
assimilate(String, Delimiter);
}
if (match_fragment(String, Delimiter, LenDelim))
{
assimilate(String, Delimiter);
}
i++;
String++;
}
String -= i;
delete[] String;
return ContainerS;
}
示例：
int main(int argc, char*argv[])
{
StringSplit ss = "This:CUT:is:CUT:an:CUT:example:CUT:cstring";
vector<char*> Split = ss.split_cstr(":CUT:");
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
将输出：
这是一实例cst环
int main(int argc, char*argv[])
{
StringSplit ss = "This:is:an:example:cstring";
vector<char*> Split = ss.split_cstr(':');
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
int main(int argc, char*argv[])
{
string mystring = "This[SPLIT]is[SPLIT]an[SPLIT]example[SPLIT]string";
StringSplit ss = mystring;
vector<string> Split = ss.split_string("[SPLIT]");
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
int main(int argc, char*argv[])
{
string mystring = "This|is|an|example|string";
StringSplit ss = mystring;
vector<string> Split = ss.split_string('|');
for (int i = 0; i < Split.size(); i++)
{
cout << Split[i] << endl;
}
return 0;
}
要保留空条目（默认情况下将排除空条目）：
StringSplit ss = mystring;
ss.keep_empty = true;
vector<string> Split = ss.split_string(":DELIM:");
目标是使其类似于C#的Split（）方法，其中拆分字符串非常简单：
String[] Split =
"Hey:cut:what's:cut:your:cut:name?".Split(new[]{":cut:"}, StringSplitOptions.None);
foreach(String X in Split)
{
Console.Write(X);
}
我希望其他人能像我一样觉得这很有用。
其他回答
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
// ...
}
}
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。
在getline上以“”作为标记进行循环。
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。
#include <iostream>
#include <vector>
using namespace std;
int main() {
string str = "ABC AABCD CDDD RABC GHTTYU FR";
str += " "; //dirty hack: adding extra space to the end
vector<string> v;
for (int i=0; i<(int)str.size(); i++) {
int a, b;
a = i;
for (int j=i; j<(int)str.size(); j++) {
if (str[j] == ' ') {
b = j;
i = j;
break;
}
}
v.push_back(str.substr(a, b-a));
}
for (int i=0; i<v.size(); i++) {
cout<<v[i].size()<<" "<<v[i]<<endl;
}
return 0;
}
