常用正则表达式JAVA练习笔记

//需求：在分组1中匹配meta中author属性的值
    //源串：
    //
    //another author="Zjmainstay too"
    //预期：分组1得到Zjmainstay
    //正则：
    @Test
    public void test1(){
        String source="n" +
                "another author="Zjmainstay too"";
        StringBuffer result=new StringBuffer();
        Pattern pattern = Pattern.compile(
                "]+>$",
                Pattern.MULTILINE);
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //(?<=[?&])(w+)=(w+)
    @Test
    public void test2(){
        String source="https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&rsv_idx=1&tn=44004473_2_oem_dg&wd=libreOffice&fenlei=256&rsv_pq=b08801ed0018207f&rsv_t=2577CzDgz4Kf9tObFCys6YC4CE1XepzLb1nvO8zmcYnrEwZPQxwB2GPcE8qgfx74Xu0AOEESbrA&rqlang=cn&rsv_enter=0&rsv_dl=tb&rsv_sug3=2&rsv_sug1=2&rsv_sug7=101&rsv_btype=i&prefixsug=libreOffice&rsp=3&rsv_sug4=5490";
        HashMap resultMap = new HashMap<>();
        Pattern pattern = Pattern.compile(
                "(?<=[?&])(\w+)=(\w+)",
                Pattern.DOTALL);
        Matcher matcher = pattern.matcher(source);
        int index=1;
        while(matcher.find()){
            System.out.println(index+++"."+matcher.group(1)+"="+matcher.group(2));
            resultMap.put(matcher.group(1),matcher.group(2));
        }
    }
    @Test
    public void test3(){
//        String source="https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&rsv_idx=1&tn=44004473_2_oem_dg&wd=libreOffice&fenlei=256&rsv_pq=b08801ed0018207f&rsv_t=2577CzDgz4Kf9tObFCys6YC4CE1XepzLb1nvO8zmcYnrEwZPQxwB2GPcE8qgfx74Xu0AOEESbrA&rqlang=cn&rsv_enter=0&rsv_dl=tb&rsv_sug3=2&rsv_sug1=2&rsv_sug7=101&rsv_btype=i&prefixsug=libreOffice&rsp=3&rsv_sug4=5490";
        String source="https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&rsv_idx=1&tn=44004473_2_oem_dg&wd=libreOffice&fenl" +
                "ei=256&rsv_pq=b08801ed0018207f&rsv_t_a_C=2577CzDgz4Kf9tObFCys6YC4CE1XepzLb1nvO8zmcYnrEwZPQxwB2GPcE8qgf" +
                "x74Xu0AOEESbrA&rqlang=cn&rsv_enter=0&rsv_dl=tb&rsv_sug3=2&rsv_sug1=2&rsv_sug7=101&rsv_btype=i&prefixsug=libreOffice&rsp=3&rsv_sug4=5490&a_b_c=123";
        StringBuffer result=new StringBuffer();
        Pattern pattern = Pattern.compile(
                "(_\w)",
                Pattern.DOTALL);
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            String valueBe=matcher.group(1);
            String valueAf=valueBe.substring(1).toUpperCase();
            matcher.appendReplacement(result,valueAf);
        }
        matcher.appendTail(result);
        System.out.println(result.toString());
    }
    //需求：匹配每行字母个数是偶数个的数据，每行数据不为空，正则不能存在分组1
    //源串：
    //a
    //ab
    //abc
    //abcd
    //预期：
    //匹配得到 ab 和 abcd，不包含分组1
    @Test
    public void test4(){
        String source="an" +
                "abn" +
                "abcn" +
                "abcdn" +
                "alksadn" +
                "asdfan" +
                "iiksn";
        Pattern pattern = Pattern.compile(
                "^(?:[\w][\w])+$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            //匹配无分组
            System.out.println(source.substring(matcher.start(),matcher.end()));
        }
    }
    //需求：匹配由 A/S/D/F 4个字母(区分大小写)组成的长度为3字符串
    //源串：
    //ABC
    //ASD
    //ADS
    //ASF
    //BBC
    //A|S
    //A|D
    //ASDF
    @Test
    public void test5(){
        String source="ABCn" +
                "ASDn" +
                "ADSn" +
                "ASFn" +
                "BBCn" +
                "A|Sn" +
                "A|Dn" +
                "ASDF";
        Pattern pattern = Pattern.compile(
                "^[ASDF][ASDF][ASDF]$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(source.substring(matcher.start(),matcher.end()));
        }
    }
    //sadf|affa&*^ds|asdf上课ds|2343|测试
    //取第一个|跟最后一个|中间已|分隔的数据内容
    @Test
    public void test6(){
        String source="sadf|affa&*^ds|asdf上课ds|2343|测试";
        Pattern pattern = Pattern.compile(
                "(?<=\|)(.*?)(?=\|)",
                Pattern.DOTALL
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //需求：匹配每行数据中以.jpg/.jpeg/.png/.gif结尾的图片名称（含后缀）
    //源串：
    //image.jpg
    //image.jpeg
    //image.png
    //image.gif
    //not_image.txt
    //not_image.doc
    //not_image.xls
    //not_image.ppt
    //预期：匹配 image.jpg/image.jpeg/image.png/image.gif 4个结果
    @Test
    public void test7(){
        String source="image.jpgn" +
                "image.jpegn" +
                "image.pngn" +
                "image.gifn" +
                "not_image.txtn" +
                "not_image.docn" +
                "not_image.xlsn" +
                "not_image.ppt";
        Pattern pattern = Pattern.compile(
                "^([\w\W]+?)(?<=\.jpg|\.jpeg|\.png|\.gif)$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //匹配连续相同3次的数字
    //源串：
    //111
    //121
    //112
    //222
    //预期：匹配 111/222 两组数据
    @Test
    public void test8(){
        String source="111n" +
                "121n" +
                "112n" +
                "222";
        Pattern pattern = Pattern.compile(
                "^(\d)\1\1$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(source.substring(matcher.start(),matcher.end()));
        }
    }
    //分别使用单行模式和普通模式匹配id="author"的div中数据，div标签不在同一行
    //源串：
    //
    //Zjmainstay
    //
    //预期：Zjmainstay
    @Test
    public void test9(){
        String source="n" +
                "Zjmainstayn" +
                "n" +
                "n" +
                "Zjmainstay1n" +
                "";
        Pattern pattern = Pattern.compile(
                "(?<=id="author"\s{0,100}>\s{0,100})\w+(?=\s*<\/div>)"
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(source.substring(matcher.start(),matcher.end()));
        }
    }
    //需求：匹配每行中包含“作者”或者“读者”的数据
    //源串：
    //本文的作者是Zjmainstay
    //本文有很多读者
    //读者可以是任何一个地方的人
    //这里的任何一个地方说明读者也能在国外
    //什么乱七八糟的推理
    //你不匹配我，凭什么要我推荐你的博客 www.zjmainstay.cn
    //预期：匹配
    //本文的作者是Zjmainstay
    //本文有很多读者
    //读者可以是任何一个地方的人
    //这里的任何一个地方说明读者也能在国外
    @Test
    public void test10(){
        String source="本文的作者是Zjmainstayn" +
                "本文有很多读者n" +
                "读者可以是任何一个地方的人n" +
                "这里的任何一个地方说明读者也能在国外n" +
                "什么乱七八糟的推理n" +
                "你不匹配我，凭什么要我推荐你的博客 www.zjmainstay.cn";
        Pattern pattern = Pattern.compile(
                "^.*(作者|读者).*$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(source.substring(matcher.start(),matcher.end()));
        }
    }
    //匹配多种或条件的数据，有特殊限制（不使用环视）
    //需求：匹配每行中“读者”在开头或结尾的数据
    //源串：
    //本文作者是Zjmainstay，有很多读者
    //读者可以是任何一个地方的人
    //这里的任何一个地方说明读者也能在国外
    //预期：匹配
    //本文作者是Zjmainstay，有很多读者
    //读者可以是任何一个地方的人
    @Test
    public void test11(){
        String source="本文作者是Zjmainstay，有很多读者n" +
                "读者可以是任何一个地方的人n" +
                "这里的任何一个地方说明读者也能在国外";
        Pattern pattern = Pattern.compile(
                "(^读者.*$|^.*读者$)",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //匹配多种或条件的数据，有特殊限制（使用环视）
    //需求：匹配每行中“读者”在开头或结尾的数据
    //源串：
    //本文作者是Zjmainstay，有很多读者
    //读者可以是任何一个地方的人
    //这里的任何一个地方说明读者也能在国外
    //预期：匹配
    //本文作者是Zjmainstay，有很多读者
    //读者可以是任何一个地方的人
    @Test
    public void test12(){
        String source="本文作者是Zjmainstay，有很多读者n" +
                "读者可以是任何一个地方的人n" +
                "这里的任何一个地方说明读者也能在国外";
        Pattern pattern = Pattern.compile(
                "^((?=.*^读者).*$|.*(?<=读者$))$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //需求：校验密码必须包含字母、数字和特殊字符，6-16位，假定特殊字符为 -_= 三个字符
    //源串：
    //12345
    //123456
    //1234561234561234
    //12345612345612345
    //a1234
    //a12345
    //-1234
    //-12345
    //a-123
    //a-1234
    //a-1234a-1234a-12
    //a-1234a-1234a-1234
    //aaaaa
    //aaaaaa
    //-_=-_
    //-_=-_=
    //预期：匹配
    //a-1234
    //a-1234a-1234a-12
    @Test
    public void test13(){
        String source="12345n" +
                "123456n" +
                "1234561234561234n" +
                "12345612345612345n" +
                "a1234n" +
                "a12345n" +
                "-1234n" +
                "-12345n" +
                "a-123n" +
                "a-1234n" +
                "a-1234a-1234a-12n" +
                "a-1234a-1234a-1234n" +
                "aaaaan" +
                "aaaaaan" +
                "-_=-_n" +
                "-_=-_=";
        Pattern pattern = Pattern.compile(
                "(?=.*[a-zA-Z])(?=.*\d)(?=.*[-_=])^.{6,16}$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(source.substring(matcher.start(),matcher.end()));
        }
    }
    //特殊限制（环视否定）
    //（8.1）使用d{1,3}匹配1-999的数据，不能以0开头
    //需求：使用d{1,3}匹配每行中1-999的数据，不能以0开头
    //源串：
    //1
    //10
    //100
    //999
    //1000
    //01
    //001
    //预期：匹配
    //1
    //10
    //100
    //999
    @Test
    public void test14(){
        String source="1n" +
                "10n" +
                "100n" +
                "999n" +
                "1000n" +
                "01n" +
                "001";
        Pattern pattern = Pattern.compile(
                "(?!.*^0)^\d{1,3}$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(source.substring(matcher.start(),matcher.end()));
        }
    }
    //匹配除了span标签外的所有标签
    //需求：匹配除了内容标签外的所有内容格式标签
    //源串：
    //匹配我
    //不匹配我
    //
匹配我
    //匹配我
    //预期：匹配
    //匹配我
    //
匹配我
    //匹配我
    @Test
    public void test15(){
        String source="匹配我n" +
                "不匹配我n" +
                "
匹配我
n" +
                "匹配我n";
        Pattern pattern = Pattern.compile(
                "^<(?!.*span)(.*)$",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //需求：给源串每个链接加上http://www.zjmainstay.cn前缀
    //源串：
    //正则文章合集（All In One)
    //正则入门教程
    //正则高级教程
    //正则环视详解
    //PHP cURL应用
    //预期：替换得到
    //正则文章合集（All In One)
    //正则入门教程
    //正则高级教程
    //正则环视详解
    //PHP cURL应用
    @Test
    public void test16(){
        String source= "正则文章合集（All In One)n" +
                "正则入门教程n" +
                "正则高级教程n" +
                "正则环视详解n" +
                "PHP cURL应用";
        StringBuffer result=new StringBuffer();
        Pattern pattern = Pattern.compile(
                "(?<=href=")(\/)",
                Pattern.MULTILINE
        );
        Matcher matcher = pattern.matcher(source);
        String replaceStr="http://www.zjmainstay.cn/";
        while(matcher.find()){
            matcher.appendReplacement(result,replaceStr);
        }
        matcher.appendTail(result);
        System.out.println(result);
    }
    //需求：将每行特定格式数据格式化为SQL语句
    //源串：
    //1 2017-04-11 Zjmainstay
    //2 2017-04-12 Nobody
    //3 2017-04-13 Somebody
    //预期：替换得到
    //INSERT INTO table_log(`id`, `created_at`, `author`) values('1', '2017-04-11', 'Zjmainstay');
    //INSERT INTO table_log(`id`, `created_at`, `author`) values('2', '2017-04-12', 'Nobody');
    //INSERT INTO table_log(`id`, `created_at`, `author`) values('3', '2017-04-13', 'Somebody');
    @Test
    public void test17(){
        String source="1 2017-04-11 Zjmainstayn" +
                "2 2017-04-12 Nobodyn" +
                "3 2017-04-13 Somebody";
        Matcher matcher = Pattern.compile(
                "^([\w])\s([\w-]+)\s([\w]+)",
                Pattern.MULTILINE
        ).matcher(source);
        String format="INSERT INTO table_log(`id`, `created_at`, `author`) values('$1', '$2', '$3');";
        while(matcher.find()){
            System.out.println(matcher.replaceAll(format));
        }
    }
    //需求：匹配html标签的属性值，属性值可以由双引号、单引号、无单双引号定界
    //源串：
    //
    //预期：分组匹配
    //I'm Zjmainstay
    //author
    //2017
    //27
    @Test
    public void test18(){
        String source="";
        Matcher matcher = Pattern.compile(
                "(?<==)(["']?)(.*?)\1[\s>]",
                Pattern.DOTALL
        ).matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(2));
        }
    }
    //需求：匹配0.00-100.00的数值，可以有0-2位小数，不能以小数点结尾，不能以2个以上的0开头
    //思路：(100|10-99|0-9) + 0-2小数位 + 排除小数点结尾、2个以上0开头的情况
    //源串：
    //0
    //1
    //0.0
    //0.00
    //9.00
    //18.00
    //27.0
    //36.00
    //45.00
    //54.00
    //63.00
    //72.00
    //81.00
    //90.00
    //99.99
    //100.00
    //0.
    //001
    //100.01
    //100.001
    //101
    //预期：匹配0.00~100.00
    @Test
    public void test19(){
        String source="0n" +
                "1n" +
                "0.0n" +
                "0.00n" +
                "9.00n" +
                "18.00n" +
                "27.0n" +
                "36.00n" +
                "35.n" +
                "45.00n" +
                "54.00n" +
                "63.00n" +
                "72.00n" +
                "81.00n" +
                "90.00n" +
                "99.99n" +
                "100.00n" +
                "0.n" +
                "001n" +
                "100.01n" +
                "100.001n" +
                "101";
        Matcher matcher = Pattern.compile(
                "(?!.*^00)^(([0-9]|(?:[1-9]\d))(?:\.\d{1,2})?|100.00)(?!<\.$)$",
                Pattern.MULTILINE
        ).matcher(source);
        while(matcher.find()){
            System.out.println(source.substring(matcher.start(),matcher.end()));
        }
    }
    //匹配链接中的文件名
    //需求：利用贪婪模式，分组1得到每行链接中的文件名
    //源串：
    //http://localhost.com/a/b/c/d/file1.txt
    //https://localhost.com/a/b/file2long.jpg
    //预期：分组0匹配行数据，分组1匹配文件名
    //file1.txt
    //file2long.jpg
    @Test
    public void test20(){
        String source="http://localhost.com/a/b/c/d/file1.txtn" +
                "https://localhost.com/a/b/file2long.jpg";
        Matcher matcher = Pattern.compile(
                "\/([\w\.]+)$",
                Pattern.MULTILINE
        ).matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //限定字符贪婪优化匹配性能
    //需求：匹配div id="author"的标签内容
    //源串：
    //Zjmainstay
    //预期：利用贪婪模式去掉div中的噪点（无关数据），分组1匹配到Zjmainstay
    //正则：
    @Test
    public void test21(){
        String source="Zjmainstay";
        Matcher matcher = Pattern.compile(
                "]+>(.*)<\/div>",
                Pattern.DOTALL
        ).matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //需求：匹配p标签内容
    //源串：
    //
内容1
内容2
    //预期：
    //在分组1中匹配到内容1和内容2
    @Test
    public void test22(){
        String source="
内容1
内容2
";
        Matcher matcher = Pattern.compile(
                "
(.*?)<\/p>",
                Pattern.DOTALL
        ).matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //需求：在分组1中匹配css或script的链接
    //源串：
    //
    //
    //预期：
    //main.min.js
    //main.css
    @Test
    public void test23(){
        String source="n" +
                "";
        Matcher matcher = Pattern.compile(
                "(?:src="|href=")([\w\W]+?)(?=")",
                Pattern.MULTILINE
        ).matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //需求：表达式格式固定，提取其中的数值
    //源串：
    //(20+170)-5*1/5=?
    //预期：
    //A:20
    //B:170
    //C:5
    //D:1
    //E:5
    //F:?
    @Test
    public void test24(){
        String source="(20+170)-5*1/5=?";
        Matcher matcher = Pattern.compile(
                "\((\d+)\+(\d+)\)\-(\d+)\*(\d+)\/(\d+)=(\?)",
                Pattern.DOTALL
        ).matcher(source);
        while(matcher.find()){
            System.out.println("A:"+matcher.group(1));
            System.out.println("B:"+matcher.group(2));
            System.out.println("C:"+matcher.group(3));
            System.out.println("D:"+matcher.group(4));
            System.out.println("E:"+matcher.group(5));
            System.out.println("F:"+matcher.group(6));
        }
    }
    //需求：在不对/转义的情况下匹配p标签内容
    //源串：
    //
内容1
内容2
    //预期：
    //在分组1中匹配到内容1和内容2
    @Test
    public void test25(){
        String source="
内容1
内容2
";
        Matcher matcher = Pattern.compile(
                "
(.*?)(?=<)",
                Pattern.DOTALL
        ).matcher(source);
        while(matcher.find()){
            System.out.println(matcher.group(1));
        }
    }
    //需求：匹配内容为数字的div
    //源串：
    //ABC123
    //预期：
    //123
    //错误正则：/d+