如何在 java中使用 Antlr4 处理文本

た入场券 2021-12-09 06:57 782阅读 0赞

需求：文件中的每一行数据都以 ”~@~“ 分隔开，读取文件，将对应属性保存到对象的对应属性。

文本：

01~@~0101~@~AE040802~@~bo123~@~BO20141011~@~AC1234~@~2017-11-11~@~0~@~0~@~1.2~@~10000000.00~@~20000.22~@~2019-10-10~@~2020-10-10~@~365
    C

对应对象：

package com.xmlParsing.model;
    
    import java.math.BigDecimal;
    import java.util.Date;
    
    /**
     * 子公司借款-计息.
     *
     * @author ch
     * @version 1.0.0
     * @since 1.0.0
     *
     * Created at 2019-07-13 11:31
     */
    public class CapInterestPacket {
    
      /*  业务一级类别 Y
       * 01 资金投资业务  */
      private String businessClass;
    
      /*  业务二级类别 Y
       * 0101 资金投资业务-子公司借款 */
      private String businessClassTwo;
    
      /*  业务事件类型 Y
       * AE040802 子公司借款-计息 */
      private String eventType;
    
      /*  核算分类 Y  */
      private String acctClass;
    
      /*  批次号   */
      private String batchNo;
    
      /*  借款协议编号 Y 子公司借款记录唯一标识 */
      private String agreementSerialNo;
    
      /*  业务发生日期 N  */
      private Date businessDate;
    
      /*  是否已封包 Y 0：否、1：是；*/
      private Integer isPackaged;
    
      /*  是否已转让 Y 0：否、1：是；*/
      private Integer isTransfered;
    
      /*  借款余额 Y  */
      private BigDecimal borrowAmount;
    
      /*  借款利率 N */
      private BigDecimal loanRate;
    
      /*  本次计息金额 Y  */
      private BigDecimal enLocalInterest;
    
      /*  匡息开始日 Y */
      private Date startDate;
    
      /*  匡息终止日 Y */
      private Date endDate;
    
      /*  匡算天数 N  */
      private Integer calDays;
    
      /* 状态码 */
      private String code;
    
      /* 信息描述 */
      private String desc;
    
      public String getBusinessClass() {
        return businessClass;
      }
    
      public void setBusinessClass(String businessClass) {
        this.businessClass = businessClass;
      }
    
      public String getBusinessClassTwo() {
        return businessClassTwo;
      }
    
      public void setBusinessClassTwo(String businessClassTwo) {
        this.businessClassTwo = businessClassTwo;
      }
    
      public String getEventType() {
        return eventType;
      }
    
      public void setEventType(String eventType) {
        this.eventType = eventType;
      }
    
      public String getAcctClass() {
        return acctClass;
      }
    
      public void setAcctClass(String acctClass) {
        this.acctClass = acctClass;
      }
    
      public String getBatchNo() {
        return batchNo;
      }
    
      public void setBatchNo(String batchNo) {
        this.batchNo = batchNo;
      }
    
      public String getAgreementSerialNo() {
        return agreementSerialNo;
      }
    
      public void setAgreementSerialNo(String agreementSerialNo) {
        this.agreementSerialNo = agreementSerialNo;
      }
    
      public Date getBusinessDate() {
        return businessDate;
      }
    
      public void setBusinessDate(Date businessDate) {
        this.businessDate = businessDate;
      }
    
      public Integer getIsPackaged() {
        return isPackaged;
      }
    
      public void setIsPackaged(Integer isPackaged) {
        this.isPackaged = isPackaged;
      }
    
      public Integer getIsTransfered() {
        return isTransfered;
      }
    
      public void setIsTransfered(Integer isTransfered) {
        this.isTransfered = isTransfered;
      }
    
      public BigDecimal getBorrowAmount() {
        return borrowAmount;
      }
    
      public void setBorrowAmount(BigDecimal borrowAmount) {
        this.borrowAmount = borrowAmount;
      }
    
      public BigDecimal getLoanRate() {
        return loanRate;
      }
    
      public void setLoanRate(BigDecimal loanRate) {
        this.loanRate = loanRate;
      }
    
      public BigDecimal getEnLocalInterest() {
        return enLocalInterest;
      }
    
      public void setEnLocalInterest(BigDecimal enLocalInterest) {
        this.enLocalInterest = enLocalInterest;
      }
    
      public Date getStartDate() {
        return startDate;
      }
    
      public void setStartDate(Date startDate) {
        this.startDate = startDate;
      }
    
      public Date getEndDate() {
        return endDate;
      }
    
      public void setEndDate(Date endDate) {
        this.endDate = endDate;
      }
    
      public Integer getCalDays() {
        return calDays;
      }
    
      public void setCalDays(Integer calDays) {
        this.calDays = calDays;
      }
    
      @Override
      public String toString() {
        return "CapInterestPacket{" +
            "businessClass='" + businessClass + '\'' +
            ", businessClassTwo='" + businessClassTwo + '\'' +
            ", eventType='" + eventType + '\'' +
            ", acctClass='" + acctClass + '\'' +
            ", batchNo='" + batchNo + '\'' +
            ", agreementSerialNo='" + agreementSerialNo + '\'' +
            ", businessDate=" + businessDate +
            ", isPackaged=" + isPackaged +
            ", isTransfered=" + isTransfered +
            ", borrowAmount=" + borrowAmount +
            ", loanRate=" + loanRate +
            ", enLocalInterest=" + enLocalInterest +
            ", startDate=" + startDate +
            ", endDate=" + endDate +
            ", calDays=" + calDays +
            ", code='" + code + '\'' +
            ", desc='" + desc + '\'' +
            '}';
      }
    
      public String getCode() {
        return code;
      }
    
      public void setCode(String code) {
        this.code = code;
      }
    
      public String getDesc() {
        return desc;
      }
    
      public void setDesc(String desc) {
        this.desc = desc;
      }
    
    }

--------------------

准备工作：

idea 下载 ANTLR V4 grammar plugin 插件

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5oYW9fY19o_size_16_color_FFFFFF_t_70][]

加入 maven 配置 依赖和插件

<dependency>
    	<groupId>org.antlr</groupId>
    	<artifactId>antlr4</artifactId>
    	<version>4.7.2</version>
     </dependency>

<build>
    	<plugins>
    		<plugin>
    			<groupId>org.springframework.boot</groupId>
    			<artifactId>spring-boot-maven-plugin</artifactId>
    		</plugin>
    		<plugin>
    			<groupId>org.antlr</groupId>
    			<artifactId>antlr4-maven-plugin</artifactId>
    			<version>4.3</version>
    			<executions>
    				<execution>
    					<id>antlr</id>
    					<goals>
    						<goal>antlr4</goal>
    					</goals>
    					<phase>none</phase>
    				</execution>
    			</executions>
    			
    				
    				
    				
    			
    		</plugin>
    	</plugins>
    </build>

新建.g4 文件并配置

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5oYW9fY19o_size_16_color_FFFFFF_t_70 1][]

规则可以自己定义

grammar Dsl;   //定义规则文件grammar
    
    //options{filter=true;}  //指定 filter 选项
    
    // 抽取器辅助词法定义
    txtFrg :
      businessClass'~@~' businessClasstwo  '~@~' eventType  '~@~' acctClass '~@~' batchNo '~@~'agreementSerialNo  '~@~' businessDate '~@~' isPackaged '~@~' isTransfered  '~@~' borrowAmount  '~@~' loanRate '~@~' enlocalInterest '~@~' startDate '~@~' endDate '~@~' calDays;
    
    
    businessClass
      :BUSINESSCLASS;
    
    businessClasstwo
      :BUSINESSCLASSTWO;
    
    eventType
      :EVENTTYPE;
    
    acctClass
      :ACCTCLASS;
    
    batchNo
      :BATCHNO;
    
    agreementSerialNo
      :AGREEMENTSERIALNO;
    
    businessDate
      :BUSINESSDATE;
    
    isPackaged
      :ISPACKAGED;
    
    isTransfered
      :ISTRANSFERED;
    
    borrowAmount
      :BORROWAMOUNT;
    
    loanRate
      :LOANRATE;
    
    enlocalInterest
      :ENLOCALINTEREST;
    
    startDate
      :STARTDATE;
    
    endDate
      :ENDDATE;
    
    calDays
      :CALDAYS;
    
    
    fragment
    // 业务一级类别.  01 资金投资业务
    BUSINESSCLASS : [0-9][0-9];
    
    
    // 业务二级类别.  0101 资金投资业务-子公司借款
    BUSINESSCLASSTWO: [0-9]+;
    
    
    // 业务时间类别. AE040802 子公司借款-计息
    EVENTTYPE : [a-zA-Z][a-zA-Z][0-9]+;
    
    
    // 核算分类
    ACCTCLASS : [a-zA-Z][a-zA-Z][0-9]+;
    
    
    // 批次号
    BATCHNO : [a-zA-Z][a-zA-Z][0-9]+;
    
    
    // 借款协议号
    AGREEMENTSERIALNO : [a-zA-Z][a-zA-Z][0-9]+;
    
    // 业务发生日期
    BUSINESSDATE : (('19'|'20')[0-9]+)'-'([0-9][0-9])'-'(('0'|'1'|'2'|'3')[0-9]) ;
    
    
    // 是否已封包
    ISPACKAGED : '0'|'1' ;
    
    
    // 是否已转让
    ISTRANSFERED : '0'|'1';
    
    
    // 借款余额
    BORROWAMOUNT : [0-9]+[.][0-9]* ;
    
    
    // 借款利率
    LOANRATE : [0-9]+[.][0-9]* ;
    
    
    // 本次计息金额
    ENLOCALINTEREST : [0-9]+[.][0-9]* ;
    
    
    // 匡息开始日
    STARTDATE : (('19'|'20')[0-9]+)'-'([0-9][0-9])'-'(('0'|'1'|'2'|'3')[0-9]) ;
    
    
    // 匡息结束日
    ENDDATE : (('19'|'20')[0-9]+)'-'([0-9][0-9])'-'(('0'|'1'|'2'|'3')[0-9]) ;
    
    
    // 匡息天数
    CALDAYS : [0-9]+;

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5oYW9fY19o_size_16_color_FFFFFF_t_70 2][]

生成代码

![20190716160242825.png][]

或者使用 maven 的插件来 构造

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5oYW9fY19o_size_16_color_FFFFFF_t_70 3][]

编写 main 调用规则

package com.xmlParsing;
    
    import com.xmlParsing.model.CapInterestPacket;
    import com.xmlParsing.parser.DslBaseListener;
    import com.xmlParsing.parser.DslLexer;
    import com.xmlParsing.parser.DslParser;
    import com.xmlParsing.parser.DslParser.AcctClassContext;
    import com.xmlParsing.parser.DslParser.AgreementSerialNoContext;
    import com.xmlParsing.parser.DslParser.BatchNoContext;
    import com.xmlParsing.parser.DslParser.BorrowAmountContext;
    import com.xmlParsing.parser.DslParser.BusinessClassContext;
    import com.xmlParsing.parser.DslParser.BusinessClasstwoContext;
    import com.xmlParsing.parser.DslParser.BusinessDateContext;
    import com.xmlParsing.parser.DslParser.CalDaysContext;
    import com.xmlParsing.parser.DslParser.EndDateContext;
    import com.xmlParsing.parser.DslParser.EnlocalInterestContext;
    import com.xmlParsing.parser.DslParser.EventTypeContext;
    import com.xmlParsing.parser.DslParser.IsPackagedContext;
    import com.xmlParsing.parser.DslParser.IsTransferedContext;
    import com.xmlParsing.parser.DslParser.LoanRateContext;
    import com.xmlParsing.parser.DslParser.StartDateContext;
    import java.io.BufferedReader;
    import java.io.File;
    import java.io.FileReader;
    import java.math.BigDecimal;
    import java.text.ParseException;
    import java.text.SimpleDateFormat;
    import org.antlr.v4.runtime.ANTLRInputStream;
    import org.antlr.v4.runtime.CommonTokenStream;
    
    /**
     * TODO
     *
     * @author ch
     * @version 1.0.0
     * @since 1.0.0
     *
     * Created at 2019-07-16 17:20
     */
    public class AntlrTest {
    
    
      public static void main(String[] args) throws Exception {
        int len = 0;
        BufferedReader in = new BufferedReader(
            new FileReader(new File("/Users/chenhao/Desktop/xmlParsing/src/main/resources/计息.txt")));
        StringBuffer str = new StringBuffer();
        String line;
        while ((line = in.readLine()) != null) {
          if (len != 0) // 处理换行符的问题
          {
            str.append("\r\n" + line);
          } else {
            str.append(line);
          }
          len++;
        }
        in.close();
        CapInterestPacket cp = run(str.toString());
        System.out.println(str.toString());
        System.out.println(cp);
    
    
      }
    
      public static CapInterestPacket run(String expr) throws Exception {
    
        SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd");
    
        CapInterestPacket cp = new CapInterestPacket();
        //对每一个输入的字符串，构造一个 ANTLRStringStream 流 in
        ANTLRInputStream in = new ANTLRInputStream(expr);
    
        //用 in 构造词法分析器 lexer，词法分析的作用是产生记号
        DslLexer lexer = new DslLexer(in);
    
        //用词法分析器 lexer 构造一个记号流 tokens
        CommonTokenStream tokens = new CommonTokenStream(lexer);
    
        //再使用 tokens 构造语法分析器 parser,至此已经完成词法分析和语法分析的准备工作
        DslParser parser = new DslParser(tokens);
        //最终调用语法分析器的规则 prog，完成对表达式的验证
    
        parser.addParseListener(new DslBaseListener() {
    
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitIsTransfered(IsTransferedContext ctx) {
            cp.setIsTransfered(Integer.valueOf(ctx.getText()));
            super.exitIsTransfered(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitBatchNo(BatchNoContext ctx) {
            cp.setBatchNo(ctx.getText());
            super.exitBatchNo(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitEnlocalInterest(EnlocalInterestContext ctx) {
            cp.setEnLocalInterest(new BigDecimal(ctx.getText()));
            super.exitEnlocalInterest(ctx);
          }
    
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitCalDays(CalDaysContext ctx) {
            cp.setCalDays(Integer.valueOf(ctx.getText()));
            super.exitCalDays(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitAcctClass(AcctClassContext ctx) {
            cp.setAcctClass(ctx.getText());
            super.exitAcctClass(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitEndDate(EndDateContext ctx) throws ParseException {
            cp.setEndDate(sdf.parse(ctx.getText()));
            super.exitEndDate(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitBusinessClass(BusinessClassContext ctx) {
            cp.setBusinessClass(ctx.getText());
            super.exitBusinessClass(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitAgreementSerialNo(AgreementSerialNoContext ctx) {
            cp.setAgreementSerialNo(ctx.getText());
            super.exitAgreementSerialNo(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitEventType(EventTypeContext ctx) {
            cp.setEventType(ctx.getText());
            super.exitEventType(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitIsPackaged(IsPackagedContext ctx) {
            cp.setIsPackaged(Integer.valueOf(ctx.getText()));
            super.exitIsPackaged(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitBusinessDate(BusinessDateContext ctx) throws ParseException {
            cp.setBusinessDate(sdf.parse(ctx.getText()));
            super.exitBusinessDate(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitBorrowAmount(BorrowAmountContext ctx) {
            cp.setBorrowAmount(new BigDecimal(ctx.getText()));
            super.exitBorrowAmount(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitBusinessClasstwo(BusinessClasstwoContext ctx) {
            cp.setBusinessClassTwo(ctx.getText());
            super.exitBusinessClasstwo(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitLoanRate(LoanRateContext ctx) {
            cp.setLoanRate(new BigDecimal(ctx.getText()));
            super.exitLoanRate(ctx);
          }
    
          // 在读取每一个匹配规则的的属性的时候 将内容插入对象的属性
          @Override
          public void exitStartDate(StartDateContext ctx) throws ParseException {
    
            cp.setStartDate(sdf.parse(ctx.getText()));
            super.exitStartDate(ctx);
          }
    
        });
    
        parser.txtFrg();
        return cp;
    
      }
    
    
    }

调用 main 方法 输出结果：

line 1:23 mismatched input 'bo123' expecting ACCTCLASS
    line 1:31 mismatched input 'BO20141011' expecting BATCHNO
    line 1:44 mismatched input 'AC1234' expecting AGREEMENTSERIALNO
    line 1:66 mismatched input '0' expecting ISPACKAGED
    line 1:70 mismatched input '0' expecting ISTRANSFERED
    line 1:80 mismatched input '10000000.00' expecting LOANRATE
    line 1:94 mismatched input '20000.22' expecting ENLOCALINTEREST
    line 1:105 mismatched input '2019-10-10' expecting STARTDATE
    line 1:118 mismatched input '2020-10-10' expecting ENDDATE
    line 1:131 mismatched input '365' expecting CALDAYS
    01~@~0101~@~AE040802~@~bo123~@~BO20141011~@~AC1234~@~2017-11-11~@~0~@~0~@~1.2~@~10000000.00~@~20000.22~@~2019-10-10~@~2020-10-10~@~365
    CapInterestPacket{businessClass='01', businessClassTwo='0101', eventType='AE040802', acctClass='bo123', batchNo='BO20141011', agreementSerialNo='AC1234', businessDate=Sat Nov 11 00:00:00 CST 2017, isPackaged=0, isTransfered=0, borrowAmount=1.2, loanRate=10000000.00, enLocalInterest=20000.22, startDate=Thu Oct 10 00:00:00 CST 2019, endDate=Sat Oct 10 00:00:00 CST 2020, calDays=365, code='null', desc='null'}

不管是否匹配，都会调用 exit 方法，所以直接set属性即可。

参考链接 [https://www.ibm.com/developerworks/cn/java/j-lo-antlrtext/\#ibm-pcon][https_www.ibm.com_developerworks_cn_java_j-lo-antlrtext_ibm-pcon]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5oYW9fY19o_size_16_color_FFFFFF_t_70]: /images/20211208/ccd1fb0c54c64b94a037d4a4eb8d73b2.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5oYW9fY19o_size_16_color_FFFFFF_t_70 1]: /images/20211208/db5d707bf4d84632895f4c0b5e344a16.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5oYW9fY19o_size_16_color_FFFFFF_t_70 2]: /images/20211208/8c60ca99c4df4b81b976b8f0e95fb9c9.png
[20190716160242825.png]: /images/20211208/2afe913683474a99a74f32bbd187bea5.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2NoZW5oYW9fY19o_size_16_color_FFFFFF_t_70 3]: /images/20211208/b2557c869f4647309affcc6466f89402.png
[https_www.ibm.com_developerworks_cn_java_j-lo-antlrtext_ibm-pcon]: https://www.ibm.com/developerworks/cn/java/j-lo-antlrtext/#ibm-pcon