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

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"    

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;
}

还有另一个答案:这里我使用find_first_not_of字符串函数,它返回第一个不匹配delim中指定的任何字符的位置。

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;
}

输出:

    scott
    tiger
    cat

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());
}

这是一个简洁的分裂函数。我决定让背靠背分隔符返回为空字符串,但您可以很容易地检查子字符串是否为空,如果是,则不将其添加到向量。

#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;

}

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';
}