Java正则表达式之分组和替换方式

// 电话号码匹配
// 手机号段只有 13xxx 15xxx 18xxxx 17xxx
System.out.println("18304072984".matches("1[3578]\\d{9}"));   // true

// 座机号：010-65784236,0316-3312617,022-12465647,03123312336
String regex = "0\\d{2}-?\\d{8}|0\\d{3}-?\\d{7}";
String telStr = "010-43367458";
System.out.println(telStr.matches(regex));  // true

String mail = "i@jiaobuchong.com.cn";
String reg = "[a-zA-Z_0-9]+@[a-zA-Z0-9]+(\\.[a-zA-Z]+){1,2}";
System.out.println(mail.matches(reg));  // true

String input = "神探狄仁&*%$杰之四大天王@bdfbdbdfdgds23532";
String reg = "[^\\u4e00-\\u9fa5]";
input = input.replaceAll(reg, "");
System.out.println(input);   // 神探狄仁杰之四大天王

// 这个正则表达式有两个组，
// group(0) 是 \\$\\{([^{}]+?)\\}
// group(1) 是 ([^{}]+?)
String regex = "\\$\\{([^{}]+?)\\}";
Pattern pattern = Pattern.compile(regex);
String input = "${name}-babalala-${age}-${address}";

Matcher matcher = pattern.matcher(input);
System.out.println(matcher.groupCount());
// find() 像迭代器那样向前遍历输入字符串
while (matcher.find()) {
    System.out.println(matcher.group(0) + ", pos: "
            + matcher.start() + "-" + (matcher.end() - 1));
    System.out.println(matcher.group(1) + ", pos: " +
            matcher.start(1) + "-" + (matcher.end(1) - 1));
}

String regex = "(\\$\\{([^{}]+?)\\})";
Pattern pattern = Pattern.compile(regex);
String input = "${name}-babalala-${age}-${address}";

Matcher matcher = pattern.matcher(input);
// matcher.find() 方法会对 input 这个字符串多次进行匹配，如果能匹配到，这个匹配结果里就会包含多个分组，我们可以从分组里提取我们想要的结果
while (matcher.find()) {
    System.out.println(matcher.group(0) + ", pos: " + matcher.start());
    System.out.println(matcher.group(1) + ", pos: " + matcher.start(1));
    System.out.println(matcher.group(2) + ", pos: " + matcher.start(2));
}

// 这个正则表达式会提取字符串中的「数字」和「字母」
        Pattern pattern = Pattern.compile("([0-9]+).*?([a-zA-Z]+)");
        String input = "那就20200719这样吧sunny。。。。。。。122432该拿什么与眼泪抗衡twinkle";
        Matcher matcher = pattern.matcher(input);
        // 每个匹配到的子串分组的个数
        int group = matcher.groupCount();
        // 如果输入串有多个可被匹配的子串，这里会多次进行匹配
        while (matcher.find()) {
            System.out.println("匹配到的子串：" + matcher.group());  // 匹配到的子串
            for (int i = 1; i <= group; i++) {
                System.out.println("分组" + i + ": " + matcher.group(i));
            }
        }

String tel = "18304072984";
// 括号表示组，被替换的部分$n表示第n组的内容
tel = tel.replaceAll("(\\d{3})\\d{4}(\\d{4})", "$1****$2");
System.out.print(tel);   // output: 183****2984

String one = "hello girl hi hot".replaceFirst("(\\w+)\\s+(\\w+)", "$2 $1"); 
String two = "hello girl hi hot".replaceAll("(\\w+)\\s+(\\w+)", "$2 $1"); 
System.out.println(one);   // girl hello hi hot
System.out.println(two);   // girl hello hot hi

String input = "假如生活欺骗了你，，，相信吧，，，快乐的日子将会来临！！！…………";

// 重复标点符号替换
String duplicateSymbolReg = "([。？！?!，]|\\.\\.\\.|……)+";
input = input.replaceAll(duplicateSymbolReg, "$1");
System.out.println(input);

String ip = "192.68.1.254 102.49.23.013 10.10.10.10 2.2.2.2 8.109.90.30";
ip = ip.replaceAll("(\\d+)", "00$1");
System.out.println(ip);

ip = ip.replaceAll("0*(\\d{3})", "$1");
System.out.println(ip);
String[] strs = ip.split(" ");

Arrays.sort(strs);
for (String str : strs) {
    str = str.replaceAll("0*(\\d+)", "$1");
    System.out.println(str);
}

/* 这个正则表达式表示 安安静静 这样的叠词 */
String regex = "(.)\\1(.)\\2";  
System.out.println("安安静静".matches(regex));   // true
System.out.println("安静安静".matches(regex));   // false

String regex = "(..)\\1";  
System.out.println("安静安静".matches(regex));   // true
System.out.println("安安静静".matches(regex));   // false

String str = "我我...我我...我要..要要...要要...找找找一个....女女女女...朋朋朋朋朋朋...友友友友友..友.友...友...友友！！！";
        
/*将 . 去掉*/
str = str.replaceAll("\\.+", "");
System.out.println(str);

str = str.replaceAll("(.)\\1+", "$1");
System.out.println(str);

"xx12abdd12345".replaceAll("(\\d{2}).+?\\1", "");  //结果为 xx345