且构网

分享程序员开发的那些事...
且构网 - 分享程序员编程开发的那些事

以点文件的形式生成AST

更新时间:2023-12-06 16:49:34

The answer i was looking for is answered here by Bart Kiers but for people who want to generate DOT files without modifying the grammar can print a intended syntax tree by taking help from this repository. Since i did not find much documentation on dot generation in ANTLR4 and no other option other than to modify ANTLR3 grammar file, i used Federico Tomassetti example and modified it a little to generate our own DOT file.

You can print a Dot file output by:

import java.io.File;
import java.io.IOException;

import java.util.ArrayList;

import java.nio.charset.Charset;
import java.nio.file.Files;

import org.antlr.v4.runtime.ANTLRInputStream;
import org.antlr.v4.runtime.CommonTokenStream;
import org.antlr.v4.runtime.ParserRuleContext;
import org.antlr.v4.runtime.RuleContext;
import org.antlr.v4.runtime.tree.ParseTree;

public class ASTGenerator {

    static ArrayList<String> LineNum = new ArrayList<String>();
    static ArrayList<String> Type = new ArrayList<String>();
    static ArrayList<String> Content = new ArrayList<String>();

    private static String readFile() throws IOException {
        File file = new File("resource/java/Blabla.java");
        byte[] encoded = Files.readAllBytes(file.toPath());
        return new String(encoded, Charset.forName("UTF-8"));
    }

    public static void main(String args[]) throws IOException{
        String inputString = readFile();
        ANTLRInputStream input = new ANTLRInputStream(inputString);
        Java8Lexer lexer = new Java8Lexer(input);
        CommonTokenStream tokens = new CommonTokenStream(lexer);
        Java8Parser parser = new Java8Parser(tokens);
        ParserRuleContext ctx = parser.compilationUnit();

        generateAST(ctx, false, 0);

    System.out.println("digraph G {");
        printDOT();
    System.out.println("}");

    }

    private static void generateAST(RuleContext ctx, boolean verbose, int indentation) {
        boolean toBeIgnored = !verbose && ctx.getChildCount() == 1 && ctx.getChild(0) instanceof ParserRuleContext;

        if (!toBeIgnored) {
            String ruleName = Java8Parser.ruleNames[ctx.getRuleIndex()];
        LineNum.add(Integer.toString(indentation));
            Type.add(ruleName);
            Content.add(ctx.getText());
    }
        for (int i = 0; i < ctx.getChildCount(); i++) {
            ParseTree element = ctx.getChild(i);
            if (element instanceof RuleContext) {
                generateAST((RuleContext) element, verbose, indentation + (toBeIgnored ? 0 : 1));
            }
        }
    }

    private static void printDOT(){
        printLabel();
        int pos = 0;
        for(int i=1; i<LineNum.size();i++){
            pos=getPos(Integer.parseInt(LineNum.get(i))-1, i);
            System.out.println((Integer.parseInt(LineNum.get(i))-1)+Integer.toString(pos)+"->"+LineNum.get(i)+i);
        }
    }

    private static void printLabel(){
        for(int i =0; i<LineNum.size(); i++){
            System.out.println(LineNum.get(i)+i+"[label=\""+Type.get(i)+"\\n "+Content.get(i)+" \"]");
        }
    }

    private static int getPos(int n, int limit){
        int pos = 0;
        for(int i=0; i<limit;i++){
            if(Integer.parseInt(LineNum.get(i))==n){
                pos = i;
            }
        }
        return pos;
    }
}

For a source code like this:

class example{
  public static void main(){
    int a;
    a = 5;
  }
}

Output will be:

digraph G {
00[label="compilationUnit\n classexample{publicstaticvoidmain(){inta;a=5;}}<EOF> "]
11[label="normalClassDeclaration\n classexample{publicstaticvoidmain(){inta;a=5;}} "]
22[label="classBody\n {publicstaticvoidmain(){inta;a=5;}} "]
33[label="methodDeclaration\n publicstaticvoidmain(){inta;a=5;} "]
44[label="methodModifier\n public "]
45[label="methodModifier\n static "]
46[label="methodHeader\n voidmain() "]
57[label="result\n void "]
58[label="methodDeclarator\n main() "]
49[label="block\n {inta;a=5;} "]
510[label="blockStatements\n inta;a=5; "]
611[label="localVariableDeclarationStatement\n inta; "]
712[label="localVariableDeclaration\n inta "]
813[label="integralType\n int "]
814[label="variableDeclaratorId\n a "]
615[label="expressionStatement\n a=5; "]
716[label="assignment\n a=5 "]
817[label="expressionName\n a "]
818[label="assignmentOperator\n = "]
819[label="literal\n 5 "]
00->11
11->22
22->33
33->44
33->45
33->46
46->57
46->58
33->49
49->510
510->611
611->712
712->813
712->814
510->615
615->716
716->817
716->818
716->819
}

Insert this piece of output in http://viz-js.com/ You will get this as ouput:

You can also pipe the output to ast.dot file by:

java -jar path-to-jar-file.jar > ast.dot

Now this is not the perfect method but enough for me. :)

Hope this helps.