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

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;
}

其他回答

我使用指针算术。对于字符串delim,如果你对char delim满意,只需简单地删除Inner while。我希望它是正确的。如果你发现任何错误或改进,请留下评论。

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;
}

我得到这个解。这很简单,所有的打印/值都在循环中(循环后不需要检查)。

#include <iostream>
#include <string>

using std::cout;
using std::string;

int main() {
    string s = "it-+is-+working!";
    string d = "-+";

    int firstFindI = 0;
    int secendFindI = 0;
    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
    }
}

感谢@SteveWard改进了这个答案。

下面是一个使用Boost string Algorithms库和Boost Range库将一个字符串与另一个字符串分割的示例。这个解决方案的灵感来自StringAlgo库文档,请参阅Split部分。

下面是split_with_string函数的完整程序,以及全面的测试-用godbolt试试:

#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");
}

测试输出:

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"    
#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;
}

注:仅当分割后的字符串长度相等时才有效

从c++ 11开始,它可以这样做:

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) ); 

注:

这是对这个答案的一个小小的改进 参见std::regex_constants::optimize使用的优化技术