C++正则表达式

• 算法
  • regex_match
  • regex_search
  • regex_replace
• 迭代器
  • regex_iterator
  • regex_token_iterator

此文章来源于👉正则表达式库 - cppreference.com,并整理

正则表达式库提供表示正则表达式的类，正则表达式是一种用于在字符串中匹配模式的微型语言。

定义于头文件

#include <iostream>
#include <iterator>
#include <string>
#include <regex>
 
int main()
{
    std::string s = "Some people, when confronted with a problem, think "
        "\"I know, I'll use regular expressions.\" "
        "Now they have two problems.";
 
    std::regex self_regex("REGULAR EXPRESSIONS",
            std::regex_constants::ECMAScript | std::regex_constants::icase);
    if (std::regex_search(s, self_regex)) {
        std::cout << "Text contains the phrase 'regular expressions'\n";
    }
 
    std::regex word_regex("(\\w+)");
    auto words_begin = 
        std::sregex_iterator(s.begin(), s.end(), word_regex);
    auto words_end = std::sregex_iterator();
 
    std::cout << "Found "
              << std::distance(words_begin, words_end)
              << " words\n";
 
    const int N = 6;
    std::cout << "Words longer than " << N << " characters:\n";
    for (std::sregex_iterator i = words_begin; i != words_end; ++i) {
        std::smatch match = *i;
        std::string match_str = match.str();
        if (match_str.size() > N) {
            std::cout << "  " << match_str << '\n';
        }
    }
 
    std::regex long_word_regex("(\\w{7,})");
    std::string new_s = std::regex_replace(s, long_word_regex, "[$&]");
    std::cout << new_s << '\n';
}

算法#

(C++11)#

尝试匹配一个正则表达式到整个字符序列 (函数模板)

#include <iostream>
#include <string>
#include <regex>
 
int main()
{
    // 简单正则表达式匹配
    std::string fnames[] = {"foo.txt", "bar.txt", "baz.dat", "zoidberg"};
    std::regex txt_regex("[a-z]+\\.txt");
 
    for (const auto &fname : fnames) {
        std::cout << fname << ": " << std::regex_match(fname, txt_regex) << '\n';
    }   
 
    // 提取子匹配
    std::regex base_regex("([a-z]+)\\.txt");
    std::smatch base_match;
 
    for (const auto &fname : fnames) {
        if (std::regex_match(fname, base_match, base_regex)) {
            // 首个 sub_match 是整个字符串；下个
            // sub_match 是首个有括号表达式。
            if (base_match.size() == 2) {
                std::ssub_match base_sub_match = base_match[1];
                std::string base = base_sub_match.str();
                std::cout << fname << " has a base of " << base << '\n';
            }
        }
    }
 
    // 提取几个子匹配
    std::regex pieces_regex("([a-z]+)\\.([a-z]+)");
    std::smatch pieces_match;
 
    for (const auto &fname : fnames) {
        if (std::regex_match(fname, pieces_match, pieces_regex)) {
            std::cout << fname << '\n';
            for (size_t i = 0; i < pieces_match.size(); ++i) {
                std::ssub_match sub_match = pieces_match[i];
                std::string piece = sub_match.str();
                std::cout << "  submatch " << i << ": " << piece << '\n';
            }   
        }   
    }   
}

(C++11)#

尝试匹配一个正则表达式到字符序列的任何部分 (函数模板)

#include <iostream>
#include <string>
#include <regex>
 
int main()
{
    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";
        }
    }
 
    // 重复搜索（参阅 std::regex_iterator ）
    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();
}

(C++11)#

以格式化的替换文本来替换正则表达式匹配的出现位置 (函数模板)

#include <iostream>
#include <iterator>
#include <regex>
#include <string>
 
int main()
{
   std::string text = "Quick brown fox";
   std::regex vowel_re("a|e|i|o|u");
 
   // 写结果到输出迭代器
   std::regex_replace(std::ostreambuf_iterator<char>(std::cout),
                      text.begin(), text.end(), vowel_re, "*");
 
   // 构造保有结果的字符串
   std::cout << '\n' << std::regex_replace(text, vowel_re, "[$&]") << '\n';
}

迭代器#

regex_iterator 用于遍历在序列中找到的匹配正则表达式的整个集合。

(C++11)#

迭代一个字符序列中的所有正则表达式匹配 (类模板)

#include <regex>
#include <iterator>
#include <iostream>
#include <string>
 
int main()
{
    const std::string s = "Quick brown fox.";
 
    std::regex words_regex("[^\\s]+");
    auto words_begin = 
        std::sregex_iterator(s.begin(), s.end(), words_regex);
    auto words_end = std::sregex_iterator();
 
    std::cout << "Found " 
              << std::distance(words_begin, words_end) 
              << " words:\n";
 
    for (std::sregex_iterator i = words_begin; i != words_end; ++i) {
        std::smatch match = *i;                                                 
        std::string match_str = match.str(); 
        std::cout << match_str << '\n';
    }   
}

(C++11)#

迭代给定字符串中的所有正则表达式匹配中的指定子表达式，或迭代未匹配的子字符串 (类模板)

#include <fstream>
#include <iostream>
#include <algorithm>
#include <iterator>
#include <regex>
 
int main()
{
   std::string text = "Quick brown fox.";
   // 记号化（非匹配碎片）
   // 注意仅匹配二次 regex ：在获得第三值时迭代器为后缀迭代器。
   std::regex ws_re("\\s+"); // 空白符
   std::copy( std::sregex_token_iterator(text.begin(), text.end(), ws_re, -1),
              std::sregex_token_iterator(),
              std::ostream_iterator<std::string>(std::cout, "\n"));
 
   // 迭代首个子匹配
   std::string html = "<p><a href=\"http://google.com\">google</a> "
                      "< a HREF =\"http://cppreference.com\">cppreference</a>\n</p>";
   std::regex url_re("<\\s*A\\s+[^>]*href\\s*=\\s*\"([^\"]*)\"", std::regex::icase);
   std::copy( std::sregex_token_iterator(html.begin(), html.end(), url_re, 1),
              std::sregex_token_iterator(),
              std::ostream_iterator<std::string>(std::cout, "\n"));
}