C++ 正则表达式 : Conditional replace

Question

我想用正则表达式替换文本中所有不在字典中的唯一标识符上的单词。我该怎么做？也许使用回调函数？

std::string getToken(const std::smatch &m) {
    static int x = 0;
    std::string keyword = m[0].str();
    std::set<std::string> keywords = {"foo", "bar"};

    if (keywords.find(keyword) != keywords.end()) {
        return keyword;
    } else {
        return "i" + x++;
    }
}

std::string replacer(std::string text) {
    std::string ret = text;

    ret = std::regex_replace(ret , std::regex("\\b.*\\b"), getToken); // It's don't works

    return ret;
}

Answer 1

使用regex_token_iterator

#include <regex>
#include <string>
#include <sstream>
#include <set>
#include <map>

std::string replacer(std::string text) {
    std::string output_text;
    std::set<std::string> keywords = { "foo", "bar" };
    std::map<std::string, int> ids = {};

    int counter = 0;
    auto callback = [&](std::string const& m){
        std::istringstream iss(m);
        std::string n;
        if (iss >> n)
        {
            if (keywords.find(m) != keywords.end()) {
                output_text += m + " ";
            }
            else {
                if (ids.find(m) != ids.end()) {
                    output_text += "ID" + std::to_string(ids[m]) + " ";
                }
                else {
                    // not found
                    ids[m] = counter;
                    output_text += "ID" + std::to_string(counter++) + " ";
                }
            }
        }
        else
        {
            output_text += m;
        }
    };

    std::regex re("\\b\\w*\\b");
    std::sregex_token_iterator
        begin(text.begin(), text.end(), re, { -1, 0 }),
        end;
    std::for_each(begin, end, callback);
    return output_text;
}