java-在ANTLR中，如何从java文件中提取类名和方法名0.1.8

2024年9月12日11:16:01----0.1.8

目标

从一个java文件中提取出类名和方法名

java源文件

文件名是main.java，具体内容如下

import org.antlr.v4.runtime.*;
import org.antlr.v4.runtime.tree.ErrorNode;
import org.antlr.v4.runtime.tree.ParseTree;
import org.antlr.v4.runtime.tree.ParseTreeWalker;
import org.antlr.v4.runtime.tree.TerminalNode;import java.util.List;public class main {public static void main(String[] args) {//需要分析的语句String inputStr = "{42,43,{32,7+6,3+9,5,6+55},3,7+1,44}";System.out.println("input size is "+inputStr.length());//将字符串转换为ANTLR的CharStreamCharStream input = CharStreams.fromString(inputStr);//使用词法分析器分析转换后的输入Lexer lexer = new HelloLexer(input);//新建一个词法符号的缓冲区，存储生成的词法符号CommonTokenStream commonTokenStream = new CommonTokenStream(lexer);//使用语法分析器处理缓冲区的内容HelloParser helloParser = new HelloParser(commonTokenStream);//对第一个line规则进行语法分析ParseTree parseTree = helloParser.line();//获取树的子数目int childCount = parseTree.getChildCount();//打印LISP风格的树System.out.println(parseTree.toStringTree());//循环打印出子节点for (int i = 0; i < childCount; i++) {System.out.println("child " + i + ":" + parseTree.getChild(i).toStringTree());}System.out.println(" ");
//        catToDog cc=new catToDog();
//        ParseTreeWalker walker=new ParseTreeWalker();
//        walker.walk(cc,parseTree);myVisitor mv = new myVisitor();mv.visit(parseTree);}public static class myVisitor extends HelloBaseVisitor<String> {/*** {@inheritDoc}** <p>The default implementation returns the result of calling* {@link #visitChildren} on {@code ctx}.</p>*/@Overridepublic String visitLine(HelloParser.LineContext ctx) {
//            System.out.println("visitLine"+ctx.value().toString()+" text:"+ctx.getText());System.out.printf("{");return visitChildren(ctx);}/*** {@inheritDoc}** <p>The default implementation returns the result of calling* {@link #visitChildren} on {@code ctx}.</p>*/@Overridepublic String visitIntShow(HelloParser.IntShowContext ctx) {int stopInt=ctx.getParent().getStop().getCharPositionInLine()-1;
//            System.out.println("dd1:"+getLastPosition(ctx.getStop().toString()) +" "+stopInt);if(getLastPosition(ctx.getStop().toString())==stopInt){System.out.printf(Integer.toHexString(Integer.parseInt(ctx.getText()))+"},");if(getLastPosition(ctx.getStop().toString())==34){System.out.printf(Integer.toHexString(Integer.parseInt(ctx.getText()))+"}");}else{System.out.printf(Integer.toHexString(Integer.parseInt(ctx.getText()))+"},");}}else{System.out.printf(Integer.toHexString(Integer.parseInt(ctx.getText()))+",");}return visitChildren(ctx);}/*** {@inheritDoc}** <p>The default implementation returns the result of calling* {@link #visitChildren} on {@code ctx}.</p>*/@Overridepublic String visitLineShow(HelloParser.LineShowContext ctx) {return visitChildren(ctx);}/*** {@inheritDoc}** <p>The default implementation returns the result of calling* {@link #visitChildren} on {@code ctx}.</p>*/@Override public String visitGetSUM(HelloParser.GetSUMContext ctx) {int stopInt=ctx.getParent().getStop().getCharPositionInLine()-1;
//            System.out.println("dd:"+getLastPosition(ctx.INT(1).getSymbol().toString()) +" "+stopInt);if(getLastPosition(ctx.INT(1).getSymbol().toString())==stopInt){if(getLastPosition(ctx.INT(1).getSymbol().toString())==34){System.out.printf((Integer.parseInt(ctx.INT(0).toString())+Integer.parseInt(ctx.INT(1).toString()))+"}");}else{System.out.printf((Integer.parseInt(ctx.INT(0).toString())+Integer.parseInt(ctx.INT(1).toString()))+"},");}}else{System.out.printf((Integer.parseInt(ctx.INT(0).toString())+Integer.parseInt(ctx.INT(1).toString()))+",");}return "4444";}public int getLastPosition(String ruleString){// String cc="[@25,28:29='44',<3>,1:28]";String lastPositionStr=ruleString.split("=")[0].split(":")[1];return Integer.parseInt(lastPositionStr);}}
}

java的g4文件

这里使用的java.g4文件，下载地址如下

https://download.csdn.net/download/m0_60688978/89742093
https://github.com/antlr/codebuff/tree/master/grammars/org/antlr/codebuff

生成antlr代码

参考这篇文章就可以了

https://blog.csdn.net/m0_60688978/article/details/141893455

最终会生成如下java文件

D:\源码\kafka-2.1\antlr\gen\Java.interp
D:\源码\kafka-2.1\antlr\gen\Java.tokens
D:\源码\kafka-2.1\antlr\gen\JavaBaseListener.java
D:\源码\kafka-2.1\antlr\gen\JavaBaseVisitor.java
D:\源码\kafka-2.1\antlr\gen\JavaLexer.java
D:\源码\kafka-2.1\antlr\gen\JavaLexer.interp
D:\源码\kafka-2.1\antlr\gen\JavaLexer.tokens
D:\源码\kafka-2.1\antlr\gen\JavaListener.java
D:\源码\kafka-2.1\antlr\gen\JavaParser.java
D:\源码\kafka-2.1\antlr\gen\JavaVisitor.java

最终代码

里面由一个main方法，和一个继承了JavaBaseListener类的自定义类，实现了几个需要的方法。使用walk类去触发遍历。

import org.antlr.v4.runtime.*;
import org.antlr.v4.runtime.tree.ParseTree;
import org.antlr.v4.runtime.tree.ParseTreeWalker;import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.nio.file.Path;/*** https://github.com/antlr/codebuff/blob/master/grammars/org/antlr/codebuff/Java8.g4*/
public class javamain {public static JavaParser javaParser;public static void main(String[] args) throws IOException {
//        String inputStr = "{42,43,{32,7+6,3+9,5,6+55},3,7+1,44}";
//        System.out.println("input size is "+inputStr.length());//将字符串转换为ANTLR的CharStream
//        CharStream input = CharStreams.fromString(inputStr);CharStream input =CharStreams.fromStream(new FileInputStream("D:\\源码\\kafka-2.1\\antlr\\src\\main.java"));//使用词法分析器分析转换后的输入Lexer lexer = new JavaLexer(input);//新建一个词法符号的缓冲区，存储生成的词法符号CommonTokenStream commonTokenStream = new CommonTokenStream(lexer);//使用语法分析器处理缓冲区的内容javaParser = new JavaParser(commonTokenStream);//对第一个line规则进行语法分析ParseTree parseTree = javaParser.compilationUnit();//获取树的子数目int childCount = parseTree.getChildCount();//打印LISP风格的树System.out.println(parseTree.toStringTree());//循环打印出子节点for (int i = 0; i < childCount; i++) {System.out.println("child " + i + ":" + parseTree.getChild(i).toStringTree());}System.out.println(" ");recognizeJava cc=new recognizeJava();ParseTreeWalker walker=new ParseTreeWalker();walker.walk(cc,parseTree);//        main.myVisitor mv = new main.myVisitor();
//        mv.visit(parseTree);}public static class recognizeJava extends JavaBaseListener{/*** {@inheritDoc}** <p>The default implementation does nothing.</p>*/@Override public void enterClassDeclaration(JavaParser.ClassDeclarationContext ctx) {System.out.printf(ctx.CLASS()+" "+ctx.Identifier().getText()+"{\n");}/*** {@inheritDoc}** <p>The default implementation does nothing.</p>*/@Override public void exitClassDeclaration(JavaParser.ClassDeclarationContext ctx) {System.out.printf("}\n");}/*** {@inheritDoc}** <p>The default implementation does nothing.</p>*/@Override public void enterMethodDeclaration(JavaParser.MethodDeclarationContext ctx) {TokenStream tokens = javaParser.getTokenStream();
//            System.out.printf(ctx.getStart().getText()+" ");String type="void";if(ctx.typeSpec()!=null){type=tokens.getText(ctx.typeSpec());}System.out.printf(type+" "+ctx.Identifier()+ctx.formalParameters().getText()+"{");}/*** {@inheritDoc}** <p>The default implementation does nothing.</p>*/@Override public void exitMethodDeclaration(JavaParser.MethodDeclarationContext ctx) {System.out.printf("}\n");}/*** {@inheritDoc}** <p>The default implementation does nothing.</p>*/@Override public void enterClassOrInterfaceModifier(JavaParser.ClassOrInterfaceModifierContext ctx) {
//            System.out.println(":"+ctx.getParent().getParent().getStart().getText());if("public".equals(ctx.getParent().getParent().getStart().getText())){//这里写死的办法需要优化一下if("static".equals(ctx.getText())){System.out.printf(ctx.getText()+" ");}else{System.out.printf("    "+ctx.getText()+" ");}}else if("@".equals(ctx.getParent().getParent().getStart().getText())){System.out.printf("\n        "+ctx.getText()+" ");}else{System.out.printf(ctx.getText()+" ");}//            System.out.printf(ctx.getParent().getParent().getStart().getText()+":"+ctx.getText()+" ");}/*** {@inheritDoc}** <p>The default implementation does nothing.</p>*/@Override public void exitClassOrInterfaceModifier(JavaParser.ClassOrInterfaceModifierContext ctx) { }/*** {@inheritDoc}** <p>The default implementation does nothing.</p>*/@Override public void enterFormalParameters(JavaParser.FormalParametersContext ctx) { }/*** {@inheritDoc}** <p>The default implementation does nothing.</p>*/@Override public void exitFormalParameters(JavaParser.FormalParametersContext ctx) { }}
}

调测结果

虽然不完美，但是基本的能提取了，提取到的类和方法如下

public class main{public static void main(String[]args){}public static class myVisitor{@Override public String visitLine(HelloParser.LineContextctx){}@Override public String visitIntShow(HelloParser.IntShowContextctx){}@Override public String visitLineShow(HelloParser.LineShowContextctx){}@Override public String visitGetSUM(HelloParser.GetSUMContextctx){}public int getLastPosition(StringruleString){}
}
}

阶段性总结

1. 再一次体会到了Listener遍历是从树顶到树脚，遍历到哪个词法规则，就会去自定义Listener中执行对应的方法。比如enterClassOrInterfaceModifier表示public或static，在遍历它语句public static时就会执行enterClassOrInterfaceModifier这个方法两次。
2. 这篇中只使用了重写了五个方法：enterClassOrInterfaceModifier、exitMethodDeclaration、enterMethodDeclaration、exitClassDeclaration、enterClassDeclaration。
3. TokenStream tokens = javaParser.getTokenStream()，token内容打印出来就是源文件的内容。其他常用的方法如下

tokens.getTokenSource().getLine()：获取内容的行数，包括了EOF，所以你看到文件只有125行，这查询出来是126，是因为包括了EOF标记