C++正则表达式

百度的笔试测试居然是用c++写一个简单正则表达式匹配。。。像regex/chrono/random这些库，我基本上都是用的时候再查，因为要记的东西还是比较多(其实不多)。那就顺便做个记录。

1.regex_search进行查找，而非全字符匹配

2.regex_match进行全字符匹配

3.std::sregex_iterator 指向所有匹配到的字符，依次遍历可以得到所有匹配的子串，类型是smatch。

4.使用regex_search匹配到的字符类型为smatch或cmatch,以smatch为例子，调用smatch::str()获得匹配的字符，smatch::prefix()获得前缀，smatch::suffix()获得后缀,显然，通过后缀我们可以一直遍历到所有匹配的字符，这似乎在暗示c++的匹配是非贪婪匹配。而对于当前smatch,smatch::size是匹配到的串的数量+子表达式的数量和。也就是说smatch[0]是整个子串，smatch[1]-smatch[size-1]是子表达式内容。

std::sregex_iterator 进行regex_search

    const std::string s = "Quick brown fox.";
 
    std::regex words_regex("[^\\s]+");//拒绝空白
    auto words_begin = std::sregex_iterator(s.begin(), s.end(), words_regex);
    auto words_end = std::sregex_iterator();//无效迭代器
 
    std::cout << "Found " 
              << std::distance(words_begin, words_end) //匹配个数
              << " words:\n";
 
    for (std::sregex_iterator i = words_begin; i != words_end; ++i) {
        std::smatch match = *i;//smatch,cmatch对应一次匹配                                                 
        std::string match_str = match.str(); 
        std::cout << match_str << '\n';
    }  

    std::string log(R"(
        Speed:    366
        Mass:    35
        Speed:    378
        Mass:    32
        Speed:    400
    Mass:    30)");
    std::regex r(R"(Speed:\t\d*)");
    std::smatch sm;
    while(regex_search(log, sm, r))
    {
        std::cout << sm.str() << '\n';
        log = sm.suffix();
    }
 
    // C 风格字符串演示
    std::cmatch cm;
    if(std::regex_search("this is a test", cm, std::regex("test"))) 
        std::cout << "\nFound " << cm[0] << " at position " << cm.prefix().length();

    std::string lines[] = {"Roses are #ff0000",
                           "violets are #0000ff",
                           "all of my base are belong to you"};
 
    std::regex color_regex("#([a-f0-9]{2})"
                            "([a-f0-9]{2})"
                            "([a-f0-9]{2})");
 
    // 简单匹配
    for (const auto &line : lines) {
        std::cout << line << ": " << std::boolalpha
                  << std::regex_search(line, color_regex) << '\n';
    }   
    std::cout << '\n';
 
    // 展示每个匹配中有标记子表达式的内容
    std::smatch color_match;
    for (const auto& line : lines) {
        if(std::regex_search(line, color_match, color_regex)) {
            std::cout << "matches for '" << line << "'\n";
            std::cout << "Prefix: '" << color_match.prefix() << "'\n";
            for (size_t i = 0; i < color_match.size(); ++i) 
                std::cout << i << ": " << color_match[i] << '\n';
            std::cout << "Suffix: '" << color_match.suffix() << "\'\n\n";
        }
    }

        std::string target("192.168.1.144:8080");
        std::regex re("([\\d]{1,3}.)([\\d]{1,3}.)([\\d]{1,3}.)[\\d]+");
        std::smatch sm;

        std::cout << sm.size() << '\n';

        std::regex_search(target, sm, re);
        std::cout << sm.size() << '\n';//4，一个ip地址和3个子表达式通过operator[]访问

 

转载于:https://www.cnblogs.com/lsaejn/p/9895323.html