正则表达式常见困惑与实际操作(速查指南)

[z|f]ood  # 会意外匹配 "|ood"
(z|f)ood   # 正确匹配 "zood" 或 "food" 或 “|ood”

	   // 断言（提取价格数字但不包含货币符号）
	   "price: $100".match(/(?<=\$)\d+/); // → ["100"]
	   
	   // 捕获（同时获取货币符号和数字）
	   "price: $100".match(/(\$)(\d+)/);  // → ["$100", "$", "100"]
		[0]	"$100"	完整匹配的字符串
		[1]	"$"	第一个捕获组 (\$) 匹配的内容
		[2]	"100"	第二个捕获组 (\d+) 匹配的内容

//heeeeellll ---> // heeeeellll
#heeeeellll ---> # heeeeellll  
(?<!:)(//)(\s.*|[\u4e00-\u9fff].*)
(#)(\s.*|[\u4e00-\u9fff].*)
$1 $2

#查找：function\s(\w+)\((.*)\)
#替换：const $1 = ($2)  => 

结果：
function screencheck()
const screencheck = ()  =>

查找：<([\w|.]+)>([\w|.]+)
替换：$2 as $1

结果：
controller as functioncontroller
<functioncontroller>controller

std::cmatch m;
auto ret = std::regex_match("<xml>value</xml>", m, std::regex("<(.*)>(.*)</xml>"));
if (ret)
{
	std::cout << m.str() << std::endl;
	std::cout << m.length() << std::endl;
	std::cout << m.position() << std::endl;
}

// 遍历匹配内容
for (auto i = 0; i < m.size(); ++i)
{
	// 两种方式都可以 输出括号()捕获的子串
	std::cout << m[i].str() << " " << m.str(i) << std::endl;
}

-------------------------------
<xml>value</xml>
16
0

<xml>value</xml> <xml>value</xml>
xml xml
value value
xml xml
-------------------------------

std::cmatch m;
auto ret = std::regex_match("123<xml>value</xml>456", m, std::regex("<(.*)>(.*)</xml>"));
if (ret)
{
	for (auto& elem : m)
		std::cout << elem << std::endl;
}
std::cout << "prefix:" << m.prefix() << std::endl;
std::cout << "suffix:" << m.suffix() << std::endl;

-------------------------------
<xml>value</xml>
xml
value
xml

prefix:123
suffix:456
-------------------------------

// 注意：如果有多个符合的内容
std::regex reg("<(.*)>(.*)</(.*)>");
std::string content("123<xml>value</xml>456<widget>center</widget>hahaha<vertical>window</vertical>the end");
std::smatch m;
auto pos = content.cbegin();
auto end = content.cend();
for (; std::regex_search(pos, end, m, reg); pos = m.suffix().first)
{
	std::cout << "----------------" << std::endl;
	std::cout << m.str() << std::endl;
	std::cout << m.str(1) << std::endl;
	std::cout << m.str(2) << std::endl;
	std::cout << m.str(3) << std::endl;
}

-------------------------------
<xml>value</xml>
xml
value
xml
----------------
<widget>center</widget>
widget
center
widget
----------------
<vertical>window</vertical>
vertical
window
vertical
-------------------------------

string str = "hello_2018!";	

regex pattern("hello");	
cout << regex_replace(str, pattern, "") << endl;	//输出：_2018，将hello替换为""
cout << regex_replace(str, pattern, "hi") << endl;	//输出：hi_2018，将hello替换为hi

regex pattern2("(.{3})(.{2})_(\\d{4})");				//匹配3个任意字符+2个任意字符+下划线+4个数字
cout << regex_replace(str, pattern2, "$1$3") << endl;	//输出：hel2018，将字符串替换为第一个和第三个表达式匹配的内容
cout << regex_replace(str, pattern2, "$1$3$2") << endl;	//输出：hel2018lo，交换位置顺序

var str = "aaabbbcccaaabbbccc";

// match
var res = str.match(/aaa/); // 没有使用g选项
输出：[ 'aaa', index: 0, input: 'aaabbbcccaaabbbccc' ]

var res = str.match(/aaa/g); // g(全局匹配) 使用g选项，全局匹配
输出：[ 'aaa', 'aaa' ]

// exec
var res =/aaa/.exec(str);
输出：[ 'aaa', index: 0, input: 'aaabbbcccaaabbbccc' ]

var res =/aaa/g.exec(str);
输出：[ 'aaa', index: 0, input: 'aaabbbcccaaabbbccc' ]

var res = /ccc([0-9]+)aaa/.exec("aaabbbccc1234aaabbbcccaaabbbccc5678aaabbbccc");
输出：[ 'ccc1234aaa', '1234', index: 6, input: 'aaabbbccc1234aaabbbccc' ]

var res = /ccc([0-9]+)aaa/g.exec("aaabbbccc1234aaabbbcccaaabbbccc5678aaabbbccc");
"ttt.md".match(/(.*).md/)[1]; //返回匹配数组

输出：[ 'ccc1234aaa', '1234', index: 6, input: 'aaabbbccc1234aaabbbcccaaabbbccc5678aaabbbccc' ][ 'ccc5678aaa', '5678', index: 28, input: 'aaabbbccc1234aaabbbcccaaabbbccc5678aaabbbccc' ]

/.*\.md$/g.exec("ttt.md")[1]; //返回匹配数组

// search
var res = "aaabbbcccaaabbbccc".search(/ccc/)
输出： 6

var res = "aaabbbcccaaabbbccc".replace(/aaa/, '111′);
输出： 111bbbcccaaabbbccc

// split
var res = "aaa,bbb,ccc".split(/,/)
输出： [ 'aaa', 'bbb', 'ccc' ]
var res = "aaa,bbb:ccc@ddd#eee".split(/[,:@#]/)
输出： [ 'aaa', 'bbb', 'ccc', 'ddd', 'eee' ]
var res = "aaa,bbb:ccc@ddd#eee".split(/[,:@#]/,3)
输出： [ 'aaa', 'bbb', 'ccc' ]

import re

# 1. 邮箱验证
emails = ["test@example.com", "invalid@.com", "name@domain.org"]
pattern = r'^[\w\.-]+@[\w\.-]+\.[a-za-z]{2,6}$'
for email in emails:
    if re.match(pattern, email):
        print(f"✅ 有效邮箱: {email}")
    else:
        print(f"❌ 无效邮箱: {email}")

# 2. 提取日期信息
text = "会议时间: 2023-08-15, 截止日期: 2024-01-20"
dates = re.findall(r'(\d{4})-(\d{2})-(\d{2})', text)
for year, month, day in dates:
    print(f"📅 日期: {year}年{month}月{day}日")

# 3. 替换敏感词
content = "这个价格是500元，但vip价格是400元"
sanitized = re.sub(r'vip价格', '***', content)
print(f"🔒 脱敏内容: {sanitized}")

# 4. 分割复杂字符串
data = "alice:30;bob:25;charlie:28"
users = re.split(r'[;:]', data)
print("👥 用户数据:", users)

# 5. 提取html标签内容
html = "<div>标题</div><p>正文内容</p>"
tags = re.findall(r'<([a-z]+)>(.*?)</\1>', html)
for tag, content in tags:
    print(f"🏷️ {tag}标签内容: {content}")

# 6. 密码强度验证
passwords = ["pass123!", "weak", "strongpwd#2023"]
for pwd in passwords:
    if re.match(r'^(?=.*[a-z])(?=.*[a-z])(?=.*\d)(?=.*[!@#$%^&*]).{8,}$', pwd):
        print(f"🔐 强密码: {pwd}")
    else:
        print(f"⚠️ 弱密码: {pwd}")

# 7. 提取中文内容
text = "python3.8发布 2020年10月，支持中文变量名=很棒"
chinese = re.findall(r'[\u4e00-\u9fa5]+', text)
print("🇨🇳 中文内容:", chinese)

# 8. 匹配ip地址
ips = ["192.168.1.1", "256.0.0.1", "127.0.0.1"]
pattern = r'^((25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)\.){3}(25[0-5]|2[0-4]\d|1\d{2}|[1-9]?\d)$'
for ip in ips:
    if re.match(pattern, ip):
        print(f"🌐 有效ip: {ip}")
    else:
        print(f"🚫 无效ip: {ip}")

# 9. 多行模式匹配
text = """标题
第一行
最后一行"""
match = re.search(r'^最后一行$', text, re.multiline)
if match:
    print(f"📝 找到结尾行: '{match.group()}'")

# 10. 预编译正则提高性能
pattern = re.compile(r'\b\w{4}\b')  # 匹配4字母单词
text = "this is sample text with some four letter words"
matches = pattern.findall(text)
print("🔤 4字母单词:", matches)