如何迭代由空格分隔的单词组成的字符串中的单词?

注意,我对C字符串函数或那种字符操作/访问不感兴趣。比起效率,我更喜欢优雅。我当前的解决方案:

#include <iostream>
#include <sstream>
#include <string>

using namespace std;

int main() {
    string s = "Somewhere down the road";
    istringstream iss(s);

    do {
        string subs;
        iss >> subs;
        cout << "Substring: " << subs << endl;
    } while (iss);
}

当前回答

我喜欢将boost/regex方法用于此任务,因为它们为指定拆分条件提供了最大的灵活性。

#include <iostream>
#include <string>
#include <boost/regex.hpp>

int main() {
    std::string line("A:::line::to:split");
    const boost::regex re(":+"); // one or more colons

    // -1 means find inverse matches aka split
    boost::sregex_token_iterator tokens(line.begin(),line.end(),re,-1);
    boost::sregex_token_iterator end;

    for (; tokens != end; ++tokens)
        std::cout << *tokens << std::endl;
}

其他回答

如果您希望按某些字符分割字符串,可以使用

#include<iostream>
#include<string>
#include<vector>
#include<iterator>
#include<sstream>
#include<string>

using namespace std;
void replaceOtherChars(string &input, vector<char> &dividers)
{
    const char divider = dividers.at(0);
    int replaceIndex = 0;
    vector<char>::iterator it_begin = dividers.begin()+1,
        it_end= dividers.end();
    for(;it_begin!=it_end;++it_begin)
    {
        replaceIndex = 0;
        while(true)
        {
            replaceIndex=input.find_first_of(*it_begin,replaceIndex);
            if(replaceIndex==-1)
                break;
            input.at(replaceIndex)=divider;
        }
    }
}
vector<string> split(string str, vector<char> chars, bool missEmptySpace =true )
{
    vector<string> result;
    const char divider = chars.at(0);
    replaceOtherChars(str,chars);
    stringstream stream;
    stream<<str;    
    string temp;
    while(getline(stream,temp,divider))
    {
        if(missEmptySpace && temp.empty())
            continue;
        result.push_back(temp);
    }
    return result;
}
int main()
{
    string str ="milk, pigs.... hot-dogs ";
    vector<char> arr;
    arr.push_back(' '); arr.push_back(','); arr.push_back('.');
    vector<string> result = split(str,arr);
    vector<string>::iterator it_begin= result.begin(),
        it_end= result.end();
    for(;it_begin!=it_end;++it_begin)
    {
        cout<<*it_begin<<endl;
    }
return 0;
}

这是我对这个的看法。我必须一个字一个字地处理输入字符串,这可以通过使用空格来计数单词来完成,但我觉得这会很乏味,我应该将单词分割成向量。

#include<iostream>
#include<vector>
#include<string>
#include<stdio.h>
using namespace std;
int main()
{
    char x = '\0';
    string s = "";
    vector<string> q;
    x = getchar();
    while(x != '\n')
    {
        if(x == ' ')
        {
            q.push_back(s);
            s = "";
            x = getchar();
            continue;
        }
        s = s + x;
        x = getchar();
    }
    q.push_back(s);
    for(int i = 0; i<q.size(); i++)
        cout<<q[i]<<" ";
    return 0;
}

不处理多个空间。如果最后一个单词后面没有紧跟换行符,则它包含最后一个词的最后一个字符和换行符之间的空格。

#include <iostream>
#include <string>
#include <sstream>
#include <algorithm>
#include <iterator>
#include <vector>

int main() {
    using namespace std;
   int n=8;
    string sentence = "10 20 30 40 5 6 7 8";
    istringstream iss(sentence);

  vector<string> tokens;
copy(istream_iterator<string>(iss),
     istream_iterator<string>(),
     back_inserter(tokens));

     for(int i=0;i<n;i++){
        cout<<tokens.at(i);
     }


}

没有任何内存分配的C++17版本(std::函数除外)

void iter_words(const std::string_view& input, const std::function<void(std::string_view)>& process_word) {

    auto itr = input.begin();

    auto consume_whitespace = [&]() {
        for(; itr != input.end(); ++itr) {
            if(!isspace(*itr))
                return;
        }
    };

    auto consume_letters = [&]() {
        for(; itr != input.end(); ++itr) {
            if(isspace(*itr))
                return;
        }
    };

    while(true) {
        consume_whitespace();
        if(itr == input.end())
            return;
        auto word_start = itr - input.begin();
        consume_letters();
        auto word_end = itr - input.begin();
        process_word(input.substr(word_start, word_end - word_start));
    }
}

int main() {
    iter_words("foo bar", [](std::string_view sv) {
        std::cout << "Got word: " <<  sv << '\n';
    });
    return 0;
}

我对string和u32string~的一般实现,使用boost::algorithm::split签名。

template<typename CharT, typename UnaryPredicate>
void split(std::vector<std::basic_string<CharT>>& split_result,
           const std::basic_string<CharT>& s,
           UnaryPredicate predicate)
{
    using ST = std::basic_string<CharT>;
    using std::swap;
    std::vector<ST> tmp_result;
    auto iter = s.cbegin(),
         end_iter = s.cend();
    while (true)
    {
        /**
         * edge case: empty str -> push an empty str and exit.
         */
        auto find_iter = find_if(iter, end_iter, predicate);
        tmp_result.emplace_back(iter, find_iter);
        if (find_iter == end_iter) { break; }
        iter = ++find_iter; 
    }
    swap(tmp_result, split_result);
}


template<typename CharT>
void split(std::vector<std::basic_string<CharT>>& split_result,
           const std::basic_string<CharT>& s,
           const std::basic_string<CharT>& char_candidate)
{
    std::unordered_set<CharT> candidate_set(char_candidate.cbegin(),
                                            char_candidate.cend());
    auto predicate = [&candidate_set](const CharT& c) {
        return candidate_set.count(c) > 0U;
    };
    return split(split_result, s, predicate);
}

template<typename CharT>
void split(std::vector<std::basic_string<CharT>>& split_result,
           const std::basic_string<CharT>& s,
           const CharT* literals)
{
    return split(split_result, s, std::basic_string<CharT>(literals));
}