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<---
其他回答
没有Boost，没有字符串流，只有标准的C库与std:：string和std:：list:C库函数配合使用，便于分析，C++数据类型便于内存管理。
空白被认为是换行符、制表符和空格的任意组合。空白字符集由wschars变量建立。
#include <string>
#include <list>
#include <iostream>
#include <cstring>
using namespace std;
const char *wschars = "\t\n ";
list<string> split(const string &str)
{
const char *cstr = str.c_str();
list<string> out;
while (*cstr) { // while remaining string not empty
size_t toklen;
cstr += strspn(cstr, wschars); // skip leading whitespace
toklen = strcspn(cstr, wschars); // figure out token length
if (toklen) // if we have a token, add to list
out.push_back(string(cstr, toklen));
cstr += toklen; // skip over token
}
// ran out of string; return list
return out;
}
int main(int argc, char **argv)
{
list<string> li = split(argv[1]);
for (list<string>::iterator i = li.begin(); i != li.end(); i++)
cout << "{" << *i << "}" << endl;
return 0;
}
Run:
$ ./split ""
$ ./split "a"
{a}
$ ./split " a "
{a}
$ ./split " a b"
{a}
{b}
$ ./split " a b c"
{a}
{b}
{c}
$ ./split " a b c d "
{a}
{b}
{c}
{d}
split的尾部递归版本（本身分裂为两个函数）。除了将字符串推入列表之外，所有对变量的破坏性操作都消失了！
void split_rec(const char *cstr, list<string> &li)
{
if (*cstr) {
const size_t leadsp = strspn(cstr, wschars);
const size_t toklen = strcspn(cstr + leadsp, wschars);
if (toklen)
li.push_back(string(cstr + leadsp, toklen));
split_rec(cstr + leadsp + toklen, li);
}
}
list<string> split(const string &str)
{
list<string> out;
split_rec(str.c_str(), out);
return out;
}
到目前为止，我在Boost中使用了这个，但我需要一些不依赖它的东西，所以我得出了这个结论：
static void Split(std::vector<std::string>& lst, const std::string& input, const std::string& separators, bool remove_empty = true)
{
std::ostringstream word;
for (size_t n = 0; n < input.size(); ++n)
{
if (std::string::npos == separators.find(input[n]))
word << input[n];
else
{
if (!word.str().empty() || !remove_empty)
lst.push_back(word.str());
word.str("");
}
}
if (!word.str().empty() || !remove_empty)
lst.push_back(word.str());
}
好的一点是，在分隔符中可以传递多个字符。
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。
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；）
这是我的版本获取了Kev的来源：
#include <string>
#include <vector>
void split(vector<string> &result, string str, char delim ) {
string tmp;
string::iterator i;
result.clear();
for(i = str.begin(); i <= str.end(); ++i) {
if((const char)*i != delim && i != str.end()) {
tmp += *i;
} else {
result.push_back(tmp);
tmp = "";
}
}
}
之后，调用函数并执行以下操作：
vector<string> hosts;
split(hosts, "192.168.1.2,192.168.1.3", ',');
for( size_t i = 0; i < hosts.size(); i++){
cout << "Connecting host : " << hosts.at(i) << "..." << endl;
}
