我在c++中使用以下方法解析字符串:
using namespace std;
string parsed,input="text to be parsed";
stringstream input_stringstream(input);
if (getline(input_stringstream,parsed,' '))
{
// do some processing.
}
使用单个字符分隔符进行解析是可以的。但是如果我想使用字符串作为分隔符呢?
例子:我想拆分:
scott>=tiger
用>=作为分隔符，这样我就可以得到斯科特和老虎。
当前回答
以防将来，有人想跳出Vincenzo Pii答案的盒子函数
#include <vector>
#include <string>
std::vector<std::string> SplitString(
std::string str,
std::string delimeter)
{
std::vector<std::string> splittedStrings = {};
size_t pos = 0;
while ((pos = str.find(delimeter)) != std::string::npos)
{
std::string token = str.substr(0, pos);
if (token.length() > 0)
splittedStrings.push_back(token);
str.erase(0, pos + delimeter.length());
}
if (str.length() > 0)
splittedStrings.push_back(str);
return splittedStrings;
}
我还修复了一些错误，以便如果字符串的开头或结尾有分隔符，函数将不会返回空字符串
其他回答
功能:
std::vector<std::string> WSJCppCore::split(const std::string& sWhat, const std::string& sDelim) {
std::vector<std::string> vRet;
size_t nPos = 0;
size_t nLen = sWhat.length();
size_t nDelimLen = sDelim.length();
while (nPos < nLen) {
std::size_t nFoundPos = sWhat.find(sDelim, nPos);
if (nFoundPos != std::string::npos) {
std::string sToken = sWhat.substr(nPos, nFoundPos - nPos);
vRet.push_back(sToken);
nPos = nFoundPos + nDelimLen;
if (nFoundPos + nDelimLen == nLen) { // last delimiter
vRet.push_back("");
}
} else {
std::string sToken = sWhat.substr(nPos, nLen - nPos);
vRet.push_back(sToken);
break;
}
}
return vRet;
}
单元测试:
bool UnitTestSplit::run() {
bool bTestSuccess = true;
struct LTest {
LTest(
const std::string &sStr,
const std::string &sDelim,
const std::vector<std::string> &vExpectedVector
) {
this->sStr = sStr;
this->sDelim = sDelim;
this->vExpectedVector = vExpectedVector;
};
std::string sStr;
std::string sDelim;
std::vector<std::string> vExpectedVector;
};
std::vector<LTest> tests;
tests.push_back(LTest("1 2 3 4 5", " ", {"1", "2", "3", "4", "5"}));
tests.push_back(LTest("|1f|2п|3%^|44354|5kdasjfdre|2", "|", {"", "1f", "2п", "3%^", "44354", "5kdasjfdre", "2"}));
tests.push_back(LTest("|1f|2п|3%^|44354|5kdasjfdre|", "|", {"", "1f", "2п", "3%^", "44354", "5kdasjfdre", ""}));
tests.push_back(LTest("some1 => some2 => some3", "=>", {"some1 ", " some2 ", " some3"}));
tests.push_back(LTest("some1 => some2 => some3 =>", "=>", {"some1 ", " some2 ", " some3 ", ""}));
for (int i = 0; i < tests.size(); i++) {
LTest test = tests[i];
std::string sPrefix = "test" + std::to_string(i) + "(\"" + test.sStr + "\")";
std::vector<std::string> vSplitted = WSJCppCore::split(test.sStr, test.sDelim);
compareN(bTestSuccess, sPrefix + ": size", vSplitted.size(), test.vExpectedVector.size());
int nMin = std::min(vSplitted.size(), test.vExpectedVector.size());
for (int n = 0; n < nMin; n++) {
compareS(bTestSuccess, sPrefix + ", element: " + std::to_string(n), vSplitted[n], test.vExpectedVector[n]);
}
}
return bTestSuccess;
}
作为奖励，这里有一个分割函数和宏的代码示例，很容易使用，你可以在其中选择容器类型:
#include <iostream>
#include <vector>
#include <string>
#define split(str, delim, type) (split_fn<type<std::string>>(str, delim))
template <typename Container>
Container split_fn(const std::string& str, char delim = ' ') {
Container cont{};
std::size_t current, previous = 0;
current = str.find(delim);
while (current != std::string::npos) {
cont.push_back(str.substr(previous, current - previous));
previous = current + 1;
current = str.find(delim, previous);
}
cont.push_back(str.substr(previous, current - previous));
return cont;
}
int main() {
auto test = std::string{"This is a great test"};
auto res = split(test, ' ', std::vector);
for(auto &i : res) {
std::cout << i << ", "; // "this", "is", "a", "great", "test"
}
return 0;
}
你可以使用next函数拆分字符串:
vector<string> split(const string& str, const string& delim)
{
vector<string> tokens;
size_t prev = 0, pos = 0;
do
{
pos = str.find(delim, prev);
if (pos == string::npos) pos = str.length();
string token = str.substr(prev, pos-prev);
if (!token.empty()) tokens.push_back(token);
prev = pos + delim.length();
}
while (pos < str.length() && prev < str.length());
return tokens;
}
我查看了答案，没有看到一个基于迭代器的方法可以被送入范围循环，所以我做了一个。
这使用了c++ 17 string_views，所以它不应该分配字符串的副本。
struct StringSplit
{
struct Iterator
{
size_t tokenStart_ = 0;
size_t tokenEnd_ = 0;
std::string str_;
std::string_view view_;
std::string delimiter_;
bool done_ = false;
Iterator()
{
// End iterator.
done_ = true;
}
Iterator(std::string str, std::string delimiter)
: str_{std::move(str)}, view_{str_}, delimiter_{
std::move(delimiter)}
{
tokenEnd_ = view_.find(delimiter_, tokenStart_);
}
std::string_view operator*()
{
return view_.substr(tokenStart_, tokenEnd_ - tokenStart_);
}
Iterator &operator++()
{
if (tokenEnd_ == std::string::npos)
{
done_ = true;
return *this;
}
tokenStart_ = tokenEnd_ + delimiter_.size();
tokenEnd_ = view_.find(delimiter_, tokenStart_);
return *this;
}
bool operator!=(Iterator &other)
{
// We only check if both points to the end.
if (done_ && other.done_)
{
return false;
}
return true;
}
};
Iterator beginIter_;
StringSplit(std::string str, std::string delim)
: beginIter_{std::move(str), std::move(delim)}
{
}
Iterator begin()
{
return beginIter_;
}
Iterator end()
{
return Iterator{};
}
};
示例用法如下:
int main()
{
for (auto token : StringSplit{"<>foo<>bar<><>bar<><>baz<><>", "<>"})
{
std::cout << "TOKEN: '" << token << "'" << std::endl;
}
}
打印:
TOKEN: ''
TOKEN: 'foo'
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'baz'
TOKEN: ''
TOKEN: ''
它正确地处理字符串开头和结尾的空项。
Strtok允许您传入多个字符作为分隔符。我敢打赌，如果你传入“>=”，你的示例字符串将被正确分割(即使>和=被算作单独的分隔符)。
EDIT如果您不想使用c_str()将字符串转换为char*，您可以使用substr和find_first_of进行标记化。
string token, mystring("scott>=tiger");
while(token != mystring){
token = mystring.substr(0,mystring.find_first_of(">="));
mystring = mystring.substr(mystring.find_first_of(">=") + 1);
printf("%s ",token.c_str());
}
