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
#include <iostream>
#include <string>
#include <deque>
std::deque<std::string> split(
const std::string& line,
std::string::value_type delimiter,
bool skipEmpty = false
) {
std::deque<std::string> parts{};
if (!skipEmpty && !line.empty() && delimiter == line.at(0)) {
parts.push_back({});
}
for (const std::string::value_type& c : line) {
if (
(
c == delimiter
&&
(skipEmpty ? (!parts.empty() && !parts.back().empty()) : true)
)
||
(c != delimiter && parts.empty())
) {
parts.push_back({});
}
if (c != delimiter) {
parts.back().push_back(c);
}
}
if (skipEmpty && !parts.empty() && parts.back().empty()) {
parts.pop_back();
}
return parts;
}
void test(const std::string& line) {
std::cout << line << std::endl;
std::cout << "skipEmpty=0 |";
for (const std::string& part : split(line, ':')) {
std::cout << part << '|';
}
std::cout << std::endl;
std::cout << "skipEmpty=1 |";
for (const std::string& part : split(line, ':', true)) {
std::cout << part << '|';
}
std::cout << std::endl;
std::cout << std::endl;
}
int main() {
test("foo:bar:::baz");
test("");
test("foo");
test(":");
test("::");
test(":foo");
test("::foo");
test(":foo:");
test(":foo::");
return 0;
}
输出：
foo:bar:::baz
skipEmpty=0 |foo|bar|||baz|
skipEmpty=1 |foo|bar|baz|
skipEmpty=0 |
skipEmpty=1 |
foo
skipEmpty=0 |foo|
skipEmpty=1 |foo|
:
skipEmpty=0 |||
skipEmpty=1 |
::
skipEmpty=0 ||||
skipEmpty=1 |
:foo
skipEmpty=0 ||foo|
skipEmpty=1 |foo|
::foo
skipEmpty=0 |||foo|
skipEmpty=1 |foo|
:foo:
skipEmpty=0 ||foo||
skipEmpty=1 |foo|
:foo::
skipEmpty=0 ||foo|||
skipEmpty=1 |foo|
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。
这个答案将字符串放入字符串向量中。它使用boost库。
#include <boost/algorithm/string.hpp>
std::vector<std::string> strs;
boost::split(strs, "string to split", boost::is_any_of("\t "));
#include <iostream>
#include <regex>
using namespace std;
int main() {
string s = "foo bar baz";
regex e("\\s+");
regex_token_iterator<string::iterator> i(s.begin(), s.end(), e, -1);
regex_token_iterator<string::iterator> end;
while (i != end)
cout << " [" << *i++ << "]";
}
IMO，这是最接近python的re.split（）。有关regex_token_iterator的更多信息，请参阅cplusplus.com。-1（regex_token_iterator tor中的第四个参数）是序列中不匹配的部分，使用匹配作为分隔符。
仅为方便：
template<class V, typename T>
bool in(const V &v, const T &el) {
return std::find(v.begin(), v.end(), el) != v.end();
}
基于多个分隔符的实际拆分：
std::vector<std::string> split(const std::string &s,
const std::vector<char> &delims) {
std::vector<std::string> res;
auto stuff = [&delims](char c) { return !in(delims, c); };
auto space = [&delims](char c) { return in(delims, c); };
auto first = std::find_if(s.begin(), s.end(), stuff);
while (first != s.end()) {
auto last = std::find_if(first, s.end(), space);
res.push_back(std::string(first, last));
first = std::find_if(last + 1, s.end(), stuff);
}
return res;
}
用法：
int main() {
std::string s = " aaa, bb cc ";
for (auto el: split(s, {' ', ','}))
std::cout << el << std::endl;
return 0;
}
这是我对这个的看法。我必须一个字一个字地处理输入字符串，这可以通过使用空格来计数单词来完成，但我觉得这会很乏味，我应该将单词分割成向量。
#include<iostream>
#include<vector>
#include<string>
#include<stdio.h>
using namespace std;
int main()
{
char x = '\0';
string s = "";
vector<string> q;
x = getchar();
while(x != '\n')
{
if(x == ' ')
{
q.push_back(s);
s = "";
x = getchar();
continue;
}
s = s + x;
x = getchar();
}
q.push_back(s);
for(int i = 0; i<q.size(); i++)
cout<<q[i]<<" ";
return 0;
}
不处理多个空间。如果最后一个单词后面没有紧跟换行符，则它包含最后一个词的最后一个字符和换行符之间的空格。
