[英]Parse (split) a string in C++ using string delimiter (standard C++)
我正在使用以下內容解析 C++ 中的字符串:
using namespace std;
string parsed,input="text to be parsed";
stringstream input_stringstream(input);
if (getline(input_stringstream,parsed,' '))
{
// do some processing.
}
使用單個 char 定界符進行解析就可以了。 但是如果我想使用字符串作為分隔符怎么辦。
示例:我想拆分:
scott>=tiger
使用>=
作為分隔符,這樣我就可以得到 scott 和 tiger。
您可以使用std::string::find()
函數查找字符串分隔符的位置,然后使用std::string::substr()
獲取令牌。
例子:
std::string s = "scott>=tiger";
std::string delimiter = ">=";
std::string token = s.substr(0, s.find(delimiter)); // token is "scott"
find(const string& str, size_t pos = 0)
函數返回str
在字符串中第一次出現的位置,如果未找到字符串,則npos
。
substr(size_t pos = 0, size_t n = npos)
函數返回對象的子字符串,從位置pos
開始,長度為npos
。
如果您有多個分隔符,則在提取一個標記后,可以將其刪除(包括分隔符)以繼續進行后續提取(如果要保留原始字符串,只需使用s = s.substr(pos + delimiter.length());
):
s.erase(0, s.find(delimiter) + delimiter.length());
這樣您就可以輕松地循環獲取每個令牌。
std::string s = "scott>=tiger>=mushroom";
std::string delimiter = ">=";
size_t pos = 0;
std::string token;
while ((pos = s.find(delimiter)) != std::string::npos) {
token = s.substr(0, pos);
std::cout << token << std::endl;
s.erase(0, pos + delimiter.length());
}
std::cout << s << std::endl;
輸出:
scott
tiger
mushroom
此方法使用std::string::find
而不通過記住前一個子字符串標記的開頭和結尾來改變原始字符串。
#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);
}
根據字符串分隔符拆分字符串。 如根據字符串分隔符"-+"
拆分字符串"adsf-+qwret-+nvfkbdsj-+orthdfjgh-+dfjrleih"
" ,輸出將是{"adsf", "qwret", "nvfkbdsj", "orthdfjgh", "dfjrleih"}
#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;
}
輸出
adsf qwret nvfkbdsj orthdfjgh dfjrleih
根據字符分隔符拆分字符串。 如用分隔符"+"
分割字符串"adsf+qwer+poui+fdgh"
”會輸出{"adsf", "qwer", "poui", "fdg"h}
#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;
}
輸出
adsf qwer poui fdgh
您可以使用 next 函數來拆分字符串:
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;
}
使用 C++20 的一種方法:
#include <iostream>
#include <ranges>
#include <string_view>
int main()
{
std::string hello = "text to be parsed";
auto split = hello
| std::ranges::views::split(' ')
| std::ranges::views::transform([](auto&& str) { return std::string_view(&*str.begin(), std::ranges::distance(str)); });
for (auto&& word : split)
{
std::cout << word << std::endl;
}
}
看:
https://stackoverflow.com/a/48403210/10771848
https://en.cppreference.com/w/cpp/ranges/split_view
您也可以為此使用正則表達式:
std::vector<std::string> split(const std::string str, const std::string regex_str)
{
std::regex regexz(regex_str);
std::vector<std::string> list(std::sregex_token_iterator(str.begin(), str.end(), regexz, -1),
std::sregex_token_iterator());
return list;
}
這相當於:
std::vector<std::string> split(const std::string str, const std::string regex_str)
{
std::sregex_token_iterator token_iter(str.begin(), str.end(), regexz, -1);
std::sregex_token_iterator end;
std::vector<std::string> list;
while (token_iter != end)
{
list.emplace_back(*token_iter++);
}
return list;
}
並像這樣使用它:
#include <iostream>
#include <string>
#include <regex>
std::vector<std::string> split(const std::string str, const std::string regex_str)
{ // a yet more concise form!
return { std::sregex_token_iterator(str.begin(), str.end(), std::regex(regex_str), -1), std::sregex_token_iterator() };
}
int main()
{
std::string input_str = "lets split this";
std::string regex_str = " ";
auto tokens = split(input_str, regex_str);
for (auto& item: tokens)
{
std::cout<<item <<std::endl;
}
}
在線玩! http://cpp.sh/9sumb
您可以像平常一樣簡單地使用子字符串、字符等,或者使用實際的正則表達式來進行拆分。
它也簡潔和 C++11!
此代碼從文本中拆分行,並將每個人添加到向量中。
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;
}
調用者:
vector<string> listFilesMax = split(buffer, "\n");
strtok允許您傳入多個字符作為分隔符。 我敢打賭,如果您傳入 ">=" 您的示例字符串將被正確拆分(即使 > 和 = 被視為單獨的分隔符)。
編輯如果您不想使用c_str()
從字符串轉換為 char*,您可以使用substr和find_first_of進行標記。
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());
}
答案已經存在,但是選擇答案使用擦除功能非常昂貴,想想一些非常大的字符串(以 MB 為單位)。 因此我使用以下功能。
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;
}
我會使用boost::tokenizer
。 這是解釋如何制作適當的標記器功能的文檔:http: //www.boost.org/doc/libs/1_52_0/libs/tokenizer/tokenizerfunction.htm
這是適合您的情況的一種。
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';
}
這是我對此的看法。 它處理邊緣情況並采用可選參數從結果中刪除空條目。
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;
}
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]()
這對於字符串(或單個字符)分隔符應該非常有效。 不要忘記包含#include <sstream>
。
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();
}
}
第一個 while 循環使用字符串分隔符的第一個字符提取標記。 第二個 while 循環跳過分隔符的其余部分並在下一個標記的開頭停止。
一個非常簡單/天真的方法:
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;
}
或者您可以使用 boost 庫拆分功能:
vector<string> result;
boost::split(result, input, boost::is_any_of("\t"));
或者你可以試試 TOKEN 或 strtok:
char str[] = "DELIMIT-ME-C++";
char *token = strtok(str, "-");
while (token)
{
cout<<token;
token = strtok(NULL, "-");
}
或者你可以這樣做:
char split_with=' ';
vector<string> words;
string token;
stringstream ss(our_string);
while(getline(ss , token , split_with)) words.push_back(token);
這是一個完整的方法,可以在任何分隔符上拆分字符串並返回切碎的字符串的向量。
這是對 ryanbwork 答案的改編。 但是,如果您的字符串中有重復元素,他的檢查: if(token != mystring)
會給出錯誤的結果。 這是我對這個問題的解決方案。
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;
}
以防萬一將來有人想要Vincenzo Pii答案的開箱即用功能
#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;
}
我還修復了一些錯誤,這樣如果字符串的開頭或結尾有分隔符,函數就不會返回空字符串
由於這是C++ split string
或類似內容的最受好評的 Stack Overflow Google 搜索結果,因此我將發布一個完整的、復制/粘貼可運行示例,以顯示這兩種方法。
splitString
使用stringstream
(在大多數情況下可能是更好和更容易的選擇)
splitString2
使用find
和substr
(更手動的方法)
// 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);
}
另一個答案:這里我使用的是find_first_not_of
字符串函數,它返回與 delim 中指定的任何字符都不匹配的第一個字符的位置。
size_t find_first_not_of(const string& delim, size_t pos = 0) const noexcept;
例子:
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;
}
輸出:
scott
tiger
cat
我做這個解決方案。 這很簡單,所有打印/值都在循環中(循環后無需檢查)。
#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
}
}
此解決方案的唯一缺點是在開始時進行兩次搜索。
這與其他答案類似,但它使用的是string_view
。 所以這些只是原始字符串的視圖。 類似於 c++20 示例。 雖然這將是一個 c++17 示例。 (編輯以跳過空匹配)
#include <algorithm>
#include <iostream>
#include <string_view>
#include <vector>
std::vector<std::string_view> split(std::string_view buffer,
const std::string_view delimeter = " ") {
std::vector<std::string_view> ret{};
std::decay_t<decltype(std::string_view::npos)> pos{};
while ((pos = buffer.find(delimeter)) != std::string_view::npos) {
const auto match = buffer.substr(0, pos);
if (!match.empty()) ret.push_back(match);
buffer = buffer.substr(pos + delimeter.size());
}
if (!buffer.empty()) ret.push_back(buffer);
return ret;
}
int main() {
const auto split_values = split("1 2 3 4 5 6 7 8 9 10 ");
std::for_each(split_values.begin(), split_values.end(),
[](const auto& str) { std::cout << str << '\n'; });
return split_values.size();
}
如果您不想修改字符串(如 Vincenzo Pii 的回答)並且還想輸出最后一個標記,您可能需要使用這種方法:
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;
}
我使用指針算術。 如果您使用 char delim 來滿足字符串分隔符的 inner while ,則只需簡單地刪除 inner while 。 我希望它是正確的。 如果您發現任何錯誤或改進,請發表評論。
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;
}
這是一個簡潔的拆分函數。 我決定讓背靠背分隔符作為空字符串返回,但您可以輕松檢查子字符串是否為空,如果是,則不將其添加到向量中。
#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;
}
#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;
}
PS:僅當拆分后字符串的長度相等時才有效
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;
}
單元測試:
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;
}
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;
}
一個更簡單的解決方案是 -
您可以在多字符定界符的基礎上使用strtok
進行定界。 請記住使用strdup
以免原始字符串發生突變。
#include <stdio.h>
#include <string.h>
const char* str = "scott>=tiger";
char *token = strtok(strdup(str), ">=");
while (token != NULL)
{
printf("%s\n", token);
token = strtok(NULL, ">=");
}
此方法使用字符串查找和字符串 substr
vector<string> split(const string& str,const string delim){
vector<string> vtokens;
size_t start = 0;
size_t end = 0;
while((end = str.find(delim,start))!=string::npos){
vtokens.push_back(str.substr(start,end-start));
start = end +1;
}
vtokens.push_back(str.substr(start));
return vtokens;
}
我查看了答案,並沒有看到可以輸入范圍循環的基於迭代器的方法,所以我做了一個。
這僅返回當前令牌,而不首先創建整個令牌向量。
struct StringSplit
{
struct Iterator
{
size_t tokenStart_ = 0;
size_t tokenEnd_ = 0;
const std::string str_;
const std::string delimiter_;
bool done_ = false;
Iterator()
{
// End iterator.
done_ = true;
}
Iterator(std::string str, std::string delimiter)
: str_{std::move(str)}, delimiter_{std::move(delimiter)}
{
tokenEnd_ = str_.find(delimiter_, tokenStart_);
}
std::string operator*()
{
return str_.substr(tokenStart_, tokenEnd_ - tokenStart_);
}
Iterator &operator++()
{
if (tokenEnd_ == std::string::npos)
{
done_ = true;
return *this;
}
tokenStart_ = tokenEnd_ + delimiter_.size();
tokenEnd_ = str_.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{};
}
};
示例用法是:
int main()
{
for (auto token : StringSplit{"<>foo<>bar<><>bar<><>baz<><>", "<>"})
{
std::cout << "TOKEN: '" << token << "'" << std::endl;
}
}
哪個打印:
TOKEN: ''
TOKEN: 'foo'
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'bar'
TOKEN: ''
TOKEN: 'baz'
TOKEN: ''
TOKEN: ''
它正確處理字符串開頭和結尾的空條目。
下面是使用Boost String Algorithms庫和Boost Range庫將一個字符串與另一個字符串拆分的示例。 該解決方案的靈感來自 StringAlgo 庫文檔的(適度)建議,請參閱拆分部分。
下面是一個完整的程序,帶有split_with_string
function 以及綜合測試 -用 godbolt 試試:
#include <iostream>
#include <string>
#include <vector>
#include <boost/algorithm/string.hpp>
#include <boost/range/iterator_range.hpp>
std::vector<std::string> split_with_string(std::string_view s, std::string_view search)
{
if (search.empty()) return {std::string{s}};
std::vector<boost::iterator_range<std::string_view::iterator>> found;
boost::algorithm::ifind_all(found, s, search);
if (found.empty()) return {};
std::vector<std::string> parts;
parts.reserve(found.size() + 2); // a bit more
std::string_view::iterator part_begin = s.cbegin(), part_end;
for (auto& split_found : found)
{
// do not skip empty extracts
part_end = split_found.begin();
parts.emplace_back(part_begin, part_end);
part_begin = split_found.end();
}
if (part_end != s.end())
parts.emplace_back(part_begin, s.end());
return parts;
}
#define TEST(expr) std::cout << ((!(expr)) ? "FAIL" : "PASS") << ": " #expr "\t" << std::endl
int main()
{
auto s0 = split_with_string("adsf-+qwret-+nvfkbdsj", "");
TEST(s0.size() == 1);
TEST(s0.front() == "adsf-+qwret-+nvfkbdsj");
auto s1 = split_with_string("adsf-+qwret-+nvfkbdsj", "-+");
TEST(s1.size() == 3);
TEST(s1.front() == "adsf");
TEST(s1.back() == "nvfkbdsj");
auto s2 = split_with_string("-+adsf-+qwret-+nvfkbdsj-+", "-+");
TEST(s2.size() == 5);
TEST(s2.front() == "");
TEST(s2.back() == "");
auto s3 = split_with_string("-+adsf-+qwret-+nvfkbdsj", "-+");
TEST(s3.size() == 4);
TEST(s3.front() == "");
TEST(s3.back() == "nvfkbdsj");
auto s4 = split_with_string("adsf-+qwret-+nvfkbdsj-+", "-+");
TEST(s4.size() == 4);
TEST(s4.front() == "adsf");
TEST(s4.back() == "");
auto s5 = split_with_string("dbo.abc", "dbo.");
TEST(s5.size() == 2);
TEST(s5.front() == "");
TEST(s5.back() == "abc");
auto s6 = split_with_string("dbo.abc", ".");
TEST(s6.size() == 2);
TEST(s6.front() == "dbo");
TEST(s6.back() == "abc");
}
測試 output:
PASS: s0.size() == 1
PASS: s0.front() == "adsf-+qwret-+nvfkbdsj"
PASS: s1.size() == 3
PASS: s1.front() == "adsf"
PASS: s1.back() == "nvfkbdsj"
PASS: s2.size() == 5
PASS: s2.front() == ""
PASS: s2.back() == ""
PASS: s3.size() == 4
PASS: s3.front() == ""
PASS: s3.back() == "nvfkbdsj"
PASS: s4.size() == 4
PASS: s4.front() == "adsf"
PASS: s4.back() == ""
PASS: s5.size() == 2
PASS: s5.front() == ""
PASS: s5.back() == "abc"
PASS: s6.size() == 2
PASS: s6.front() == "dbo"
PASS: s6.back() == "abc"
作為獎勵,這是一個易於使用的拆分函數和宏的代碼示例,您可以在其中選擇容器類型:
#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;
}
從 C++11 開始,它可以這樣完成:
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) );
筆記:
std::vector<std::string> split(const std::string& s, char c) {
std::vector<std::string> v;
unsigned int ii = 0;
unsigned int j = s.find(c);
while (j < s.length()) {
v.push_back(s.substr(i, j - i));
i = ++j;
j = s.find(c, j);
if (j >= s.length()) {
v.push_back(s.substr(i, s,length()));
break;
}
}
return v;
}
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.