Java正则表达式匹配字符串提取中间值

场景一:提取SAML2报文

SAML2报文内容如下,从中提取对应的attribute name和value.

<saml:AttributeStatement>
	<saml:Attribute Name="mail">
		<saml:AttributeValue xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:type="xs:string">zhengkai.blog.csdn.net</saml:AttributeValue>
	</saml:Attribute>
	<saml:Attribute Name="cn">
		<saml:AttributeValue xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:type="xs:string">amAdmin</saml:AttributeValue>
	</saml:Attribute>
</saml:AttributeStatement>

show time

public static void main(String[] args) {
		String content = "";
		content = "<saml:AttributeStatement>";
		content += "	<saml:Attribute Name=\"mail\">";
		content += "		<saml:AttributeValue xmlns:xs=\"http://www.w3.org/2001/XMLSchema\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\" xsi:type=\"xs:string\">zhengkai.blog.csdn.net</saml:AttributeValue>";
		content += "	</saml:Attribute>";
		content += "	<saml:Attribute Name=\"cn\">";
		content += "		<saml:AttributeValue xmlns:xs=\"http://www.w3.org/2001/XMLSchema\" xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\" xsi:type=\"xs:string\">amAdmin</saml:AttributeValue>";
		content += "	</saml:Attribute>";
		content += "</saml:AttributeStatement>";
		String pattern = "\\<saml\\:Attribute Name=\\\"(?<scope>.*?)\\\"\\>[\\s\\S]*?\\<saml\\:AttributeValue[\\s\\S]*?\\>(?<value>.*?)\\<\\/saml\\:AttributeValue\\>[\\s\\S]*?\\<\\/saml\\:Attribute\\>";
		Pattern r = Pattern.compile(pattern);
		Matcher matcher = r.matcher(saml2attributeString);
		while (matcher.find()){
			String attributeName = matcher.group("scope");
			String attributeValue = matcher.group("value");
			System.out.println("attributeName->"+attributeName +",attributeValue->"+attributeValue );
		}
	}

控制台输出

$ attributeName->mail,attributeValue->zhengkai.blog.csdn.net
$ vattributeName->cn,attributeValue->amAdmin

解析

\\<saml\\:Attribute Name=\\\"(?<scope>.*?)\\\"\\>[\\s\\S]*?\\<saml\\:AttributeValue[\\s\\S]*?\\>(?<value>.*?)\\<\\/saml\\:AttributeValue\\>[\\s\\S]*?\\<\\/saml\\:Attribute\\>

1.(?.*?)是用于标识scope的方式，表示夹在中间的字符串都叫scope，可以通过matcher.group("scope")提取。

2.所有非正则的符号都需要转义，所以你会看到很多\\<或者换\\"之类的\\

3.[\\s\\S]*? 是用来匹配任意字符，表示在前后有界定的情况下(例如夹在中间的字符串)，可以忽略那些不规则字符串的匹配。

场景2:提取sql中的表名和字段

    //匹配整个ddl，将ddl分为表名，列sql部分，表注释
    private static final Pattern DDL_PATTERN = Pattern.compile("\\s*create\\s+table\\s+(?<tableName>\\S+)[^\\(]*\\((?<columnsSQL>[\\s\\S]+)\\)[^\\)]+?(comment\\s*(=|on\\s+table)\\s*'(?<tableComment>.*?)'\\s*;?)?$", Pattern.CASE_INSENSITIVE);
    //匹配列sql部分，分别解析每一列的列名 类型 和列注释
    private static final Pattern COL_PATTERN = Pattern.compile("\\s*(?<fieldName>\\S+)\\s+(?<fieldType>\\w+)\\s*(?:\\([\\s\\d,]+\\))?((?!comment).)*(comment\\s*'(?<fieldComment>.*?)')?\\s*(,|$)", Pattern.CASE_INSENSITIVE);
    public static void parse(String sql){
        Matcher matcher = DDL_PATTERN.matcher(sql);
        if (matcher.find()){
            String tableName = matcher.group("tableName");
            String tableComment = matcher.group("tableComment");
            System.out.println(tableName + "\t\t" + tableComment);
            System.out.println("==========");
            String columnsSQL = matcher.group("columnsSQL");
            if (columnsSQL != null && columnsSQL.length() > 0){
                Matcher colMatcher = COL_PATTERN.matcher(columnsSQL);
                while (colMatcher.find()){
                    String fieldName = colMatcher.group("fieldName");
                    String fieldType = colMatcher.group("fieldType");
                    String fieldComment = colMatcher.group("fieldComment");
                    if (!"key".equalsIgnoreCase(fieldType)){
                        System.out.println(fieldName + "\t\t" + fieldType + "\t\t" + fieldComment);
                    }
                }
            }
        }
    }
    public static void main(String[] args){
        System.out.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>");
        parse("CREATE TABLE `userinfo` (\n" +
                "  `user_id` int(11) NOT NULL AUTO_INCREMENT COMMENT '用户ID',\n" +
                "  `username` varchar(255) NOT NULL COMMENT '用户名',\n" +
                "  `addtime` datetime NOT NULL COMMENT '创建时间',\n" +
                "  PRIMARY KEY (`user_id`)\n" +
                ") ENGINE=InnoDB DEFAULT CHARSET=utf8 COMMENT='用户信息'");
        System.out.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>");
        parse("CREATE TABLE `USER` (\n" +
                "`ID` varchar(32) PRIMARY KEY COMMENT '主键',\n" +
                "`password` varchar(32) NOT NULL COMMENT '密码',\n" +
                "`username` varchar(32) NOT NULL COMMENT '用户'\n" +
                ") ENGINE=InnoDB DEFAULT CHARSET=utf8;");
        System.out.println(">>>>>>>>>>>>>>>>>>>>>>>>>>>>>");
        parse("CREATE TABLE `tb_amount` (\n" +
                "`ID` int(10) NOT NULL AUTO_INCREMENT,\n" +
                "`PRODUCT_CODE` varchar(50) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NOT NULL COMMENT '产品代码',\n" +
                "`GENDER` varchar(10) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '性别(male,female)',\n" +
                "`MIN_INSURED_AGE` int(3) NULL DEFAULT NULL COMMENT '最小投保年龄',\n" +
                "`MAX_INSURED_AGE` int(3) NULL DEFAULT NULL COMMENT '最大投保年龄',\n" +
                "`AMOUNT` double(10, 2) NULL DEFAULT NULL COMMENT '基本保额',\n" +
                "`PREMIUM_RATE` double(10, 2) NULL DEFAULT NULL COMMENT '基本保费',\n" +
                "`YEAR_NUM` int(3) NULL DEFAULT NULL COMMENT '缴费年限',\n" +
                "`PREMIUM_TYPE` varchar(10) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '费率类型',\n" +
                "`INSURANCE_PERIOD` varchar(10) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '保险期间(30年，60年)',\n" +
                "`INSURANCE_PERIOD_TYPE` varchar(50) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '保险期间类型(如定期年0,定期岁1,终身2,以后终身对应值：200)',\n" +
                "`PAY_MODE` varchar(10) CHARACTER SET utf8mb4 COLLATE utf8mb4_0900_ai_ci NULL DEFAULT NULL COMMENT '交费方式',\n" +
                "PRIMARY KEY (`ID`) USING BTREE\n" +
                ") ENGINE = InnoDB CHARACTER SET = utf8mb4 COLLATE = utf8mb4_0900_ai_ci ROW_FORMAT = Dynamic;");
    }

控制台输出内容:

>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
`userinfo`		用户信息
==========
`user_id`		int		用户ID
`username`		varchar		用户名
`addtime`		datetime		创建时间
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
`USER`		null
==========
`ID`		varchar		主键
`password`		varchar		密码
`username`		varchar		用户
>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
`tb_amount`		null
==========
`ID`		int		null
`PRODUCT_CODE`		varchar		产品代码
`GENDER`		varchar		性别(male,female)
`MIN_INSURED_AGE`		int		最小投保年龄
`MAX_INSURED_AGE`		int		最大投保年龄
`AMOUNT`		double		基本保额
`PREMIUM_RATE`		double		基本保费
`YEAR_NUM`		int		缴费年限
`PREMIUM_TYPE`		varchar		费率类型
`INSURANCE_PERIOD`		varchar		保险期间(30年，60年)
`INSURANCE_PERIOD_TYPE`		varchar		保险期间类型(如定期年0,定期岁1,终身2,以后终身对应值：200)
`PAY_MODE`		varchar		交费方式

以上就是极悦小编介绍的"Java正则表达式匹配字符串提取中间值"的内容，希望对大家有帮助，如有疑问，请在线咨询，有专业老师随时为您服务。