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
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());
}
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;
}
以下是我的看法。它处理边缘情况，并接受一个可选参数从结果中删除空条目。
bool endsWith(const std::string& s, const std::string& suffix)
{
return s.size() >= suffix.size() &&
s.substr(s.size() - suffix.size()) == suffix;
}
std::vector<std::string> split(const std::string& s, const std::string& delimiter, const bool removeEmptyEntries = false)
{
std::vector<std::string> tokens;
for (size_t start = 0, end; start < s.length(); start = end + delimiter.length())
{
size_t position = s.find(delimiter, start);
end = position != std::string::npos ? position : s.length();
std::string token = s.substr(start, end - start);
if (!removeEmptyEntries || !token.empty())
{
tokens.push_back(token);
}
}
if (!removeEmptyEntries &&
(s.empty() || endsWith(s, delimiter)))
{
tokens.push_back("");
}
return tokens;
}
例子
split("a-b-c", "-"); // [3]("a","b","c")
split("a--c", "-"); // [3]("a","","c")
split("-b-", "-"); // [3]("","b","")
split("--c--", "-"); // [5]("","","c","","")
split("--c--", "-", true); // [1]("c")
split("a", "-"); // [1]("a")
split("", "-"); // [1]("")
split("", "-", true); // [0]()
我会使用boost::tokenizer。下面的文档解释了如何创建适当的标记器函数:http://www.boost.org/doc/libs/1_52_0/libs/tokenizer/tokenizerfunction.htm
这里有一个对你的案子有用。
struct my_tokenizer_func
{
template<typename It>
bool operator()(It& next, It end, std::string & tok)
{
if (next == end)
return false;
char const * del = ">=";
auto pos = std::search(next, end, del, del + 2);
tok.assign(next, pos);
next = pos;
if (next != end)
std::advance(next, 2);
return true;
}
void reset() {}
};
int main()
{
std::string to_be_parsed = "1) one>=2) two>=3) three>=4) four";
for (auto i : boost::tokenizer<my_tokenizer_func>(to_be_parsed))
std::cout << i << '\n';
}
一种非常简单/幼稚的方法:
vector<string> words_seperate(string s){
vector<string> ans;
string w="";
for(auto i:s){
if(i==' '){
ans.push_back(w);
w="";
}
else{
w+=i;
}
}
ans.push_back(w);
return ans;
}
或者你可以使用boost库拆分函数:
vector<string> result;
boost::split(result, input, boost::is_any_of("\t"));
或者你可以尝试TOKEN或strtok:
char str[] = "DELIMIT-ME-C++";
char *token = strtok(str, "-");
while (token)
{
cout<<token;
token = strtok(NULL, "-");
}
或者你可以这样做:
char split_with=' ';
vector<string> words;
string token;
stringstream ss(our_string);
while(getline(ss , token , split_with)) words.push_back(token);
该方法使用std::string::find，而不改变原始字符串，记住前一个子字符串标记的开始和结束。
#include <iostream>
#include <string>
int main()
{
std::string s = "scott>=tiger";
std::string delim = ">=";
auto start = 0U;
auto end = s.find(delim);
while (end != std::string::npos)
{
std::cout << s.substr(start, end - start) << std::endl;
start = end + delim.length();
end = s.find(delim, start);
}
std::cout << s.substr(start, end);
}
