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
这类似于堆栈溢出问题：如何在C++中标记字符串？。需要Boost外部库
#include <iostream>
#include <string>
#include <boost/tokenizer.hpp>
using namespace std;
using namespace boost;
int main(int argc, char** argv)
{
string text = "token test\tstring";
char_separator<char> sep(" \t");
tokenizer<char_separator<char>> tokens(text, sep);
for (const string& t : tokens)
{
cout << t << "." << endl;
}
}
其他回答
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。
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;
}
我喜欢下面的代码，因为它将结果放入一个向量中，支持字符串作为delim，并控制保持空值。但是，那时候看起来不太好。
#include <ostream>
#include <string>
#include <vector>
#include <algorithm>
#include <iterator>
using namespace std;
vector<string> split(const string& s, const string& delim, const bool keep_empty = true) {
vector<string> result;
if (delim.empty()) {
result.push_back(s);
return result;
}
string::const_iterator substart = s.begin(), subend;
while (true) {
subend = search(substart, s.end(), delim.begin(), delim.end());
string temp(substart, subend);
if (keep_empty || !temp.empty()) {
result.push_back(temp);
}
if (subend == s.end()) {
break;
}
substart = subend + delim.size();
}
return result;
}
int main() {
const vector<string> words = split("So close no matter how far", " ");
copy(words.begin(), words.end(), ostream_iterator<string>(cout, "\n"));
}
当然，Boost有一个split（），它的部分功能与此类似。而且，如果“空白”是指任何类型的空白，那么使用Boost的split和is_any_of（）都非常有用。
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。
// adapted from a "regular" csv parse
std::string stringIn = "my csv is 10233478 NOTseparated by commas";
std::vector<std::string> commaSeparated(1);
int commaCounter = 0;
for (int i=0; i<stringIn.size(); i++) {
if (stringIn[i] == " ") {
commaSeparated.push_back("");
commaCounter++;
} else {
commaSeparated.at(commaCounter) += stringIn[i];
}
}
最后你会得到一个字符串向量，句子中的每个元素都用空格隔开。唯一的非标准资源是std:：vector（但由于涉及std:：string，我认为它是可以接受的）。
空字符串保存为单独的项。
