在C++;使用字符串分隔符(标准C+;+;) 我使用C++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。但如果我想使用字符串作为分隔符呢 示例:我要拆分:在C++;使用字符串分隔符(标准C+;+;) 我使用C++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. },c++,parsing,split,token,tokenize,C++,Parsing,Split,Token,Tokenize,使用单个字符分隔符进行解析是可以的。但如果我想使用字符串作为分隔符呢 示例:我要拆分: scott>=tiger 用=作为分隔符,这样我就可以得到scott和tiger 允许您传入多个字符作为分隔符。我打赌,如果您传入“>=”,您的示例字符串将被正确拆分(即使>和=被计为单独的分隔符) 编辑如果您不想使用c_str()将字符串转换为字符*,可以使用和进行标记化 string token, mystring("scott>=tiger"); while(token != mystri
scott>=tiger
用=
作为分隔符,这样我就可以得到scott和tiger 允许您传入多个字符作为分隔符。我打赌,如果您传入“>=”,您的示例字符串将被正确拆分(即使>和=被计为单独的分隔符)
编辑如果您不想使用c_str()
将字符串转换为字符*,可以使用和进行标记化
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());
}
我会使用
boost::tokenizer
。下面的文档解释了如何生成适当的标记器函数:
这是一个适合你的案子
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';
}
struct my\u tokenizer\u func
{
模板
bool运算符()(It&next,It end,std::string&tok)
{
如果(下一步==结束)
返回false;
字符常量*del=“>=”;
自动pos=std::搜索(下一步、结束、删除、删除+2);
tok.分配(下一步,位置);
next=pos;
如果(下一步!=结束)
标准::前进(下一步,2);
返回true;
}
void reset(){}
};
int main()
{
std::要分析的字符串=“1)一>=2)二>=3)三>=4)四”;
for(自动i:boost::tokenizer(待解析))
std::cout您可以使用该函数查找字符串分隔符的位置,然后使用获取令牌
例如:
std::string s = "scott>=tiger";
std::string delimiter = ">=";
std::string token = s.substr(0, s.find(delimiter)); // token is "scott"
int main()
{
size_t start = 0, end = 0;
std::string str = "scott>=tiger>=cat";
std::string delim = ">=";
while ((start = str.find_first_not_of(delim, end)) != std::string::npos)
{
end = str.find(delim, start); // finds the 'first' occurance from the 'start'
std::cout << str.substr(start, end - start)<<std::endl; // extract substring
}
return 0;
}
find(const string&str,size\t pos=0)
函数返回字符串中第一次出现的str
的位置,或者如果未找到该字符串
substr(size\u t pos=0,size\u t n=npos)
函数返回对象的子字符串,从位置pos
开始,长度npos
如果您有多个分隔符,在提取一个令牌后,可以删除它(包括分隔符)以继续后续提取(如果您想保留原始字符串,只需使用s=s.substr(pos+delimiter.length());
):
通过这种方式,您可以轻松地循环获取每个令牌
完整示例
此方法使用std::string::find
,不通过记住前一个子字符串标记的开始和结束来改变原始字符串
#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);
}
#包括
#包括
int main()
{
std::string s=“scott>=tiger”;
std::string delim=“>=”;
自动启动=0U;
自动结束=s.find(delim);
while(end!=std::string::npos)
{
std::cout您可以使用下一个函数拆分字符串:
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;
}
向量拆分(常量字符串和str、常量字符串和delim)
{
向量标记;
大小\u t上一个=0,位置=0;
做
{
pos=str.find(delim,prev);
如果(pos==string::npos)pos=str.length();
字符串标记=str.substr(prev,pos-prev);
如果(!token.empty())标记。向后推(token);
上一个=位置+最小长度();
}
而(pos
std::vector split(常量std::string&s,char c){
std::向量v;
无符号整数ii=0;
无符号整数j=s.find(c);
而(j=s.length()){
v、 向后推(s.substr(i,s,length());
打破
}
}
返回v;
}
如果您不想修改字符串(如Vincenzo Pii的回答)并且想输出最后一个标记,您可能需要使用以下方法:
inline std::vector<std::string> splitString( const std::string &s, const std::string &delimiter ){
std::vector<std::string> ret;
size_t start = 0;
size_t end = 0;
size_t len = 0;
std::string token;
do{ end = s.find(delimiter,start);
len = end - start;
token = s.substr(start, len);
ret.emplace_back( token );
start += len + delimiter.length();
std::cout << token << std::endl;
}while ( end != std::string::npos );
return ret;
}
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;
}
inline std::vector splitString(常量std::string&s,常量std::string&delimiter){
std::载体ret;
大小\u t开始=0;
尺寸=0;
尺寸长度=0;
字符串标记;
do{end=s.find(分隔符,开始);
len=结束-开始;
令牌=s.substr(开始,len);
返回阵地(令牌);
start+=len+分隔符.length();
std::cout这是我对此的看法。它处理边缘情况,并使用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 != 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;
}
这段代码从文本中拆分行,并将所有人添加到一个向量中
vector<string> split(char *phrase, string delimiter){
vector<string> list;
string s = string(phrase);
size_t pos = 0;
string token;
while ((pos = s.find(delimiter)) != string::npos) {
token = s.substr(0, pos);
list.push_back(token);
s.erase(0, pos + delimiter.length());
}
list.push_back(s);
return list;
}
向量拆分(字符*短语,字符串分隔符){
向量表;
字符串s=字符串(短语);
大小\u t pos=0;
字符串标记;
while((pos=s.find(delimiter))!=string::npos){
令牌=s.substr(0,位置);
列表。推回(令牌);
s、 擦除(0,pos+分隔符.length());
}
列表。向后推_(s);
退货清单;
}
召集人:
vector<string> listFilesMax = split(buffer, "\n");
vector listFilesMax=split(缓冲区“\n”);
用于字符串分隔符
基于字符串分隔符拆分字符串。例如,基于字符串分隔符拆分字符串“-+”
,输出将是{“adsf”,“qwret”,“nvfkbdsj”,“orthdfjgh”,“dfjrleih”}
输出
adsf
qwret
nvfkbdsj
orthdfjgh
dfjrleih
adsf
qwer
poui
fdgh
adsf
qwer
普伊
脱氧葡萄糖
#包括
#包括
使用名称空间std;
int split_计数(字符串str、字符分隔){
返回计数(str.begin()、str.end()、分隔符);
}
无效拆分(字符串str、字符分隔、字符串res[]){
int a=0,i=0;
while(a这是一个完整的方法,它在任何分隔符上分割字符串,并返回分割字符串的向量
这是根据ryanbwork的答案改编的。但是,如果字符串中有重复的元素,他检查:if(token!=mystring)
会给出错误的结果。这是我对该问题的解决方案
vector<string> Split(string mystring, string delimiter)
{
vector<string> subStringList;
string token;
while (true)
{
size_t findfirst = mystring.find_first_of(delimiter);
if (findfirst == string::npos) //find_first_of returns npos if it couldn't find the delimiter anymore
{
subStringList.push_back(mystring); //push back the final piece of mystring
return subStringList;
}
token = mystring.substr(0, mystring.find_first_of(delimiter));
mystring = mystring.substr(mystring.find_first_of(delimiter) + 1);
subStringList.push_back(token);
}
return subStringList;
}
向量拆分(字符串mystring,字符串分隔符)
{
向量子串表;
字符串标记;
while(true)
{
size\u t findfirst=mystring.find\u first\u of(分隔符);
if(findfirst==string::npos)//find\u first\u如果再也找不到分隔符,则返回npos
{
subStringList.push_back(mystring);//推回mystring的最后一部分
#include <iostream>
#include <sstream>
#include <vector>
using namespace std;
// for string delimiter
vector<string> split (string s, string delimiter) {
size_t pos_start = 0, pos_end, delim_len = delimiter.length();
string token;
vector<string> res;
while ((pos_end = s.find (delimiter, pos_start)) != string::npos) {
token = s.substr (pos_start, pos_end - pos_start);
pos_start = pos_end + delim_len;
res.push_back (token);
}
res.push_back (s.substr (pos_start));
return res;
}
int main() {
string str = "adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih";
string delimiter = "-+";
vector<string> v = split (str, delimiter);
for (auto i : v) cout << i << endl;
return 0;
}
adsf
qwret
nvfkbdsj
orthdfjgh
dfjrleih
#include <iostream>
#include <sstream>
#include <vector>
using namespace std;
vector<string> split (const string &s, char delim) {
vector<string> result;
stringstream ss (s);
string item;
while (getline (ss, item, delim)) {
result.push_back (item);
}
return result;
}
int main() {
string str = "adsf+qwer+poui+fdgh";
vector<string> v = split (str, '+');
for (auto i : v) cout << i << endl;
return 0;
}
adsf
qwer
poui
fdgh
#include<iostream>
#include<algorithm>
using namespace std;
int split_count(string str,char delimit){
return count(str.begin(),str.end(),delimit);
}
void split(string str,char delimit,string res[]){
int a=0,i=0;
while(a<str.size()){
res[i]=str.substr(a,str.find(delimit));
a+=res[i].size()+1;
i++;
}
}
int main(){
string a="abc.xyz.mno.def";
int x=split_count(a,'.')+1;
string res[x];
split(a,'.',res);
for(int i=0;i<x;i++)
cout<<res[i]<<endl;
return 0;
}
vector<string> Split(string mystring, string delimiter)
{
vector<string> subStringList;
string token;
while (true)
{
size_t findfirst = mystring.find_first_of(delimiter);
if (findfirst == string::npos) //find_first_of returns npos if it couldn't find the delimiter anymore
{
subStringList.push_back(mystring); //push back the final piece of mystring
return subStringList;
}
token = mystring.substr(0, mystring.find_first_of(delimiter));
mystring = mystring.substr(mystring.find_first_of(delimiter) + 1);
subStringList.push_back(token);
}
return subStringList;
}
vector<string> split(const string& i_str, const string& i_delim)
{
vector<string> result;
size_t found = i_str.find(i_delim);
size_t startIndex = 0;
while(found != string::npos)
{
result.push_back(string(i_str.begin()+startIndex, i_str.begin()+found));
startIndex = found + i_delim.size();
found = i_str.find(i_delim, startIndex);
}
if(startIndex != i_str.size())
result.push_back(string(i_str.begin()+startIndex, i_str.end()));
return result;
}
std::string input = "Alfa=,+Bravo=,+Charlie=,+Delta";
std::string delimiter = "=,+";
std::istringstream ss(input);
std::string token;
std::string::iterator it;
while(std::getline(ss, token, *(it = delimiter.begin()))) {
std::cout << token << std::endl; // Token is extracted using '='
it++;
// Skip the rest of delimiter if exists ",+"
while(it != delimiter.end() and ss.peek() == *(it)) {
it++; ss.get();
}
}
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;
}
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;
}
std::vector<std::string> parse(std::string str,std::string delim){
std::vector<std::string> tokens;
char *str_c = strdup(str.c_str());
char* token = NULL;
token = strtok(str_c, delim.c_str());
while (token != NULL) {
tokens.push_back(std::string(token));
token = strtok(NULL, delim.c_str());
}
delete[] str_c;
return tokens;
}
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;
}
vector<string> result;
boost::split(result, input, boost::is_any_of("\t"));
char str[] = "DELIMIT-ME-C++";
char *token = strtok(str, "-");
while (token)
{
cout<<token;
token = strtok(NULL, "-");
}
char split_with=' ';
vector<string> words;
string token;
stringstream ss(our_string);
while(getline(ss , token , split_with)) words.push_back(token);
// SplitString.cpp
#include <iostream>
#include <vector>
#include <string>
#include <sstream>
// function prototypes
std::vector<std::string> splitString(const std::string& str, char delim);
std::vector<std::string> splitString2(const std::string& str, char delim);
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx);
int main(void)
{
// Test cases - all will pass
std::string str = "ab,cd,ef";
//std::string str = "abcdef";
//std::string str = "";
//std::string str = ",cd,ef";
//std::string str = "ab,cd,"; // behavior of splitString and splitString2 is different for this final case only, if this case matters to you choose which one you need as applicable
std::vector<std::string> tokens = splitString(str, ',');
std::cout << "tokens: " << "\n";
if (tokens.empty())
{
std::cout << "(tokens is empty)" << "\n";
}
else
{
for (auto& token : tokens)
{
if (token == "") std::cout << "(empty string)" << "\n";
else std::cout << token << "\n";
}
}
return 0;
}
std::vector<std::string> splitString(const std::string& str, char delim)
{
std::vector<std::string> tokens;
if (str == "") return tokens;
std::string currentToken;
std::stringstream ss(str);
while (std::getline(ss, currentToken, delim))
{
tokens.push_back(currentToken);
}
return tokens;
}
std::vector<std::string> splitString2(const std::string& str, char delim)
{
std::vector<std::string> tokens;
if (str == "") return tokens;
int leftIdx = 0;
int delimIdx = str.find(delim);
int rightIdx;
while (delimIdx != std::string::npos)
{
rightIdx = delimIdx - 1;
std::string token = getSubstring(str, leftIdx, rightIdx);
tokens.push_back(token);
// prep for next time around
leftIdx = delimIdx + 1;
delimIdx = str.find(delim, delimIdx + 1);
}
rightIdx = str.size() - 1;
std::string token = getSubstring(str, leftIdx, rightIdx);
tokens.push_back(token);
return tokens;
}
std::string getSubstring(const std::string& str, int leftIdx, int rightIdx)
{
return str.substr(leftIdx, rightIdx - leftIdx + 1);
}
#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;
}
std::vector<std::string> splitString(const std::string& str,
const std::regex& regex)
{
return {std::sregex_token_iterator{str.begin(), str.end(), regex, -1},
std::sregex_token_iterator() };
}
// usually we have a predefined set of regular expressions: then
// let's build those only once and re-use them multiple times
static const std::regex regex1(R"some-reg-exp1", std::regex::optimize);
static const std::regex regex2(R"some-reg-exp2", std::regex::optimize);
static const std::regex regex3(R"some-reg-exp3", std::regex::optimize);
string str = "some string to split";
std::vector<std::string> tokens( splitString(str, regex1) );
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.push_back(std::forward<T>(t)), void()) {
c.push_back(std::forward<T>(t));
}
template<typename C, typename T>
auto insert_in_container(C& c, T&& t) -> decltype(c.insert(std::forward<T>(t)), void()) {
c.insert(std::forward<T>(t));
}
template<typename Container>
Container splitR(const std::string& input, const std::string& delims) {
Container out;
size_t delims_len = delims.size();
auto begIdx = 0u;
auto endIdx = input.find(delims, begIdx);
if (endIdx == std::string::npos && input.size() != 0u) {
insert_in_container(out, input);
}
else {
size_t w = 0;
while (endIdx != std::string::npos) {
w = endIdx - begIdx;
if (w != 0) insert_in_container(out, input.substr(begIdx, w));
begIdx = endIdx + delims_len;
endIdx = input.find(delims, begIdx);
}
w = input.length() - begIdx;
if (w != 0) insert_in_container(out, input.substr(begIdx, w));
}
return out;
}
size_t find_first_not_of(const string& delim, size_t pos = 0) const noexcept;
int main()
{
size_t start = 0, end = 0;
std::string str = "scott>=tiger>=cat";
std::string delim = ">=";
while ((start = str.find_first_not_of(delim, end)) != std::string::npos)
{
end = str.find(delim, start); // finds the 'first' occurance from the 'start'
std::cout << str.substr(start, end - start)<<std::endl; // extract substring
}
return 0;
}
scott
tiger
cat
#include <iostream>
#include <string>
using std::cout;
using std::string;
int main() {
string s = "it-+is-+working!";
string d = "-+";
int firstFindI = 0;
int secendFindI = s.find(d, 0); // find if have any at all
while (secendFindI != string::npos)
{
secendFindI = s.find(d, firstFindI);
cout << s.substr(firstFindI, secendFindI - firstFindI) << "\n"; // print sliced part
firstFindI = secendFindI + d.size(); // add to the search index
}
}
std::vector<std::string> split(std::string s, std::string delim)
{
char *p = &s[0];
char *d = &delim[0];
std::vector<std::string> res = {""};
do
{
bool is_delim = true;
char *pp = p;
char *dd = d;
while (*dd && is_delim == true)
if (*pp++ != *dd++)
is_delim = false;
if (is_delim)
{
p = pp - 1;
res.push_back("");
}
else
*(res.rbegin()) += *p;
} while (*p++);
return res;
}
#include <vector>
#include <string>
using namespace std;
vector<string> split(string to_split, string delimiter) {
size_t pos = 0;
vector<string> matches{};
do {
pos = to_split.find(delimiter);
int change_end;
if (pos == string::npos) {
pos = to_split.length() - 1;
change_end = 1;
}
else {
change_end = 0;
}
matches.push_back(to_split.substr(0, pos+change_end));
to_split.erase(0, pos+1);
}
while (!to_split.empty());
return matches;
}