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());
}
下面是一个更好的方法。它可以接受任何字符，除非您愿意，否则不会拆分行。不需要特殊的库（嗯，除了std，但谁真的认为这是一个额外的库），没有指针，没有引用，而且它是静态的。只是简单的C++。
#pragma once
#include <vector>
#include <sstream>
using namespace std;
class Helpers
{
public:
static vector<string> split(string s, char delim)
{
stringstream temp (stringstream::in | stringstream::out);
vector<string> elems(0);
if (s.size() == 0 || delim == 0)
return elems;
for(char c : s)
{
if(c == delim)
{
elems.push_back(temp.str());
temp = stringstream(stringstream::in | stringstream::out);
}
else
temp << c;
}
if (temp.str().size() > 0)
elems.push_back(temp.str());
return elems;
}
//Splits string s with a list of delimiters in delims (it's just a list, like if we wanted to
//split at the following letters, a, b, c we would make delims="abc".
static vector<string> split(string s, string delims)
{
stringstream temp (stringstream::in | stringstream::out);
vector<string> elems(0);
bool found;
if(s.size() == 0 || delims.size() == 0)
return elems;
for(char c : s)
{
found = false;
for(char d : delims)
{
if (c == d)
{
elems.push_back(temp.str());
temp = stringstream(stringstream::in | stringstream::out);
found = true;
break;
}
}
if(!found)
temp << c;
}
if(temp.str().size() > 0)
elems.push_back(temp.str());
return elems;
}
};
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。
这个呢
#include <string>
#include <vector>
using namespace std;
vector<string> split(string str, const char delim) {
vector<string> v;
string tmp;
for(string::const_iterator i; i = str.begin(); i <= str.end(); ++i) {
if(*i != delim && i != str.end()) {
tmp += *i;
} else {
v.push_back(tmp);
tmp = "";
}
}
return v;
}
这是另一种方法。。
void split_string(string text,vector<string>& words)
{
int i=0;
char ch;
string word;
while(ch=text[i++])
{
if (isspace(ch))
{
if (!word.empty())
{
words.push_back(word);
}
word = "";
}
else
{
word += ch;
}
}
if (!word.empty())
{
words.push_back(word);
}
}
