antlr parse oracle store procedure

build.bat

antlr4 Cymbol.g4
javac *.java
run Cymbol file -gui test1.sp

dot -Tpng dot.gv -o dot.png

g4

/** Simple statically-typed programming language with functions and variables
 *  taken from "Language Implementation Patterns" book.
 */
grammar Cymbol;

file:   packageDeclaration functionDecl* 'END' ID ';';

packageDeclaration
	:	'CREATE' 'OR' 'REPLACE' 'PACKAGE' 'BODY' qualifiedName 'AS'

	;

functionDecl
    :   'FUNCTION' ID ('(' formalParameters? ')')? 'RETURN' oracleType 'IS' varDecl* block 
	// FUNCTION IS_FIXED_INCOME( CUSIPID_IN IN VARCHAR2) RETURN BOOLEAN is type defs begin ... end IS_FIXED_INCOME;
    ;	

varDecl
    :   ID oracleType ';'
    ;

formalParameters
    :   formalParameter (',' formalParameter)*
    ;
formalParameter
    :   ID 'IN'? 'OUT'? oracleType ('DEFAULT' ID)?
    ;	
subBlock:  'BEGIN' stat+ 'END' ';';   
block:  'BEGIN' stat+ 'END' ID ';';   

qualifiedName
    :   ID ('.' ID)*
    ;	

oracleType : ('INT'|'NUMBER'|'VARCHAR2'|'VARCHAR'|'NVARCHAR2') ('(' DIGIT+ ')')*
			| ('NUMBER') ('(' DIGIT+ ',' DIGIT+ ')')
			| ('DATE')
			| ('BLOB')
			| ('CLOB')
                        | ('BOOLEAN')
			| ('TIMESTAMP')
			| ('REF') ('CURSOR')
			| qualifiedName ('%TYPE')
			| qualifiedName
			;	

stat:   subBlock 
    |   if_stat
    |   insert_stat
    |   delete_stat
    |   update_stat 
    |   select_stat
    |   'RETURN' expr? ';' 
    |   expr ':=' expr ';'  // assignment
    |   expr ';'          // func call
    ;

if_stat: 'IF' expr 'THEN' stat ('ELSIF' stat)? ('ELSE' stat)? 'END' 'IF' ';';
insert_stat: 'INSERT' .*? ';'; 
delete_stat: 'DELETE' .*? ';'; 
update_stat: 'UPDATE' .*? ';'; 
select_stat: 'SELECT' .*? ';'; 

expr:   ID '(' exprList? ')'    # Call   
    |   '-' expr                # Negate
    |   '!' expr                # Not
    |   expr '*' expr           # Mult
    |   expr ('+'|'-') expr     # AddSub
    |   expr '=' expr  			# IfCond
    |   expr '==' expr          # Equal
    |   expr '||' expr          # Contact
    |   ID                      # Var
    |   INT                     # Int
    |   '\'' ID '\''            # Parens
    |   '(' expr ')'            # Parens
    ;

exprList : expr (',' expr)* ;   // arg list	

ID  :   Letter (Letter | [0-9] | '_')* ;	
DIGIT : [0-9];

fragment
Letter :  [a-zA-Z];

fragment
JavaIDDigit
    :  '\u0030'..'\u0039' |
       '\u0660'..'\u0669' |
       '\u06f0'..'\u06f9' |
       '\u0966'..'\u096f' |
       '\u09e6'..'\u09ef' |
       '\u0a66'..'\u0a6f' |
       '\u0ae6'..'\u0aef' |
       '\u0b66'..'\u0b6f' |
       '\u0be7'..'\u0bef' |
       '\u0c66'..'\u0c6f' |
       '\u0ce6'..'\u0cef' |
       '\u0d66'..'\u0d6f' |
       '\u0e50'..'\u0e59' |
       '\u0ed0'..'\u0ed9' |
       '\u1040'..'\u1049'
   ;	

INT :   [0-9]+ ;   

WS  :   [ \t\n\r]+ -> skip ;   


SL_COMMENT
    :   '--' .*? '\n' -> skip
    ;

COMMENT
    :   '/*' .*? '*/'    -> channel(HIDDEN) // match anything between /* and */
    ;

/*   
varDecl
    :   type ID ('=' expr)? ';'
    ;
type:   'float' | 'int' | 'void' ; // user-defined types


K_FLOAT : 'float';
K_INT   : 'int';
K_VOID  : 'void';

fragment
LETTER : [a-zA-Z] ;


*/

test sp

CREATE OR REPLACE 
PACKAGE BODY ANTLR1
AS
FUNCTION F1
  RETURN BOOLEAN
IS
  ASSETTYPE VARCHAR2(10);
BEGIN
  ASSETTYPE := 'X';
  BEGIN
    IF (ASSETTYPE = 'E') THEN
      RETURN FALSE;
    ELSE
      RETURN TRUE;
    END IF;
  END;
  ASSETTYPE := ASSETTYPE || 'YYY';
  F1();
END F1;

FUNCTION F2(
    CUSIPID_IN IN VARCHAR2 ,
    A          IN VARCHAR2)
  RETURN BOOLEAN
IS
  ASSETTYPE VARCHAR2(10);
BEGIN
  --SELECT AUTHOR INTO ASSETTYPE FROM BASELINE WHERE AUTHOR = CUSIPID_IN;
  IF (ASSETTYPE = 'E') THEN
    RETURN FALSE;
  ELSE
    RETURN TRUE;
  END IF;
END F2;
FUNCTION F3(
    CUSIPID_IN IN VARCHAR2 )
  RETURN BOOLEAN
IS
  ASSETTYPE VARCHAR2(10);
BEGIN
  ASSETTYPE := '3';
  --SELECT AUTHOR INTO ASSETTYPE FROM BASELINE WHERE AUTHOR = CUSIPID_IN;
  IF (ASSETTYPE = 'E') THEN
    RETURN FALSE;
  ELSE
    RETURN TRUE;
  END IF;
  F2();
END F3;

FUNCTION F4(
    CUSIPID_IN IN VARCHAR2,
    V_BATCH_MODE2 OUT VARCHAR,    --BATCH WS/CTF PROCESSING MODE OR NOT
    V_BATCH_MODE3    IN OUT VARCHAR, --BATCH WS/CTF PROCESSING MODE OR NOT
    V_WASH_INIT_FLAG IN BOOLEAN DEFAULT FALSE,
    V_ALT_LOT_NUM    IN VARCHAR2 DEFAULT NULL)
  RETURN BOOLEAN
IS
  ASSETTYPE VARCHAR2(10);
  A BOOLEAN;

BEGIN
	ASSETTYPE := '4';
  A := F3('XXX');
	/*
  SELECT AUTHOR INTO ASSETTYPE FROM BASELINE WHERE AUTHOR = CUSIPID_IN;
  BEGIN
    UPDATE BASELINE SET ID = 1 WHERE 1 = 0;
  END;
  DELETE FROM BASELINE WHERE 1 = 0;
  IF (ASSETTYPE = 'E') THEN
    RETURN FALSE;
  ELSE
    RETURN TRUE;
  END IF;
  */
END F4;
/*
PROCEDURE TEST1(
    V_BATCH_MODE IN VARCHAR,      --BATCH WS/CTF PROCESSING MODE OR NOT
    V_BATCH_MODE2 OUT VARCHAR,    --BATCH WS/CTF PROCESSING MODE OR NOT
    V_BATCH_MODE3    IN OUT VARCHAR, --BATCH WS/CTF PROCESSING MODE OR NOT
    V_WASH_INIT_FLAG IN BOOLEAN DEFAULT FALSE,
    V_ALT_LOT_NUM    IN VARCHAR2 DEFAULT NULL)
IS
  TEMP_STR VARCHAR2(500);
  TEMP_BL  BOOLEAN;
BEGIN
  TEMP_BL := F1();
  INSERT INTO Z_LARGETABLE2
    ( ID, ID2
    ) VALUES
    ( 5, 2
    );
  TEMP_BL := F1;
  TEMP_BL := IS_FIXED_INCOME('XX');
  --COMM[HGHJGJG]IT;
END TEST1;
*/
END ANTLR1;

/***
 * Excerpted from "The Definitive ANTLR 4 Reference",
 * published by The Pragmatic Bookshelf.
 * Copyrights apply to this code. It may not be used to create training material, 
 * courses, books, articles, and the like. Contact us if you are in doubt.
 * We make no guarantees that this code is fit for any purpose. 
 * Visit http://www.pragmaticprogrammer.com/titles/tpantlr2 for more book information.
***/
import org.antlr.v4.runtime.*;
import org.antlr.v4.runtime.misc.MultiMap;
import org.antlr.v4.runtime.misc.OrderedHashSet;
import org.antlr.v4.runtime.tree.ParseTree;
import org.antlr.v4.runtime.tree.ParseTreeWalker;
import org.stringtemplate.v4.ST;

import java.io.FileInputStream;
import java.io.InputStream;
import java.util.Set;

public class Test {
    public static void main(String[] args) throws Exception {
        String inputFile = null;
        if ( args.length>0 ) {
        	inputFile = args[0];
        }
        else {
//        inputFile = "src/t.cymbol";
        	inputFile = "src/test1.sp";
        }
        InputStream is = System.in;
        if ( inputFile!=null ) {
            is = new FileInputStream(inputFile);
        }
        ANTLRInputStream input = new ANTLRInputStream(is);
        CymbolLexer lexer = new CymbolLexer(input);
        CommonTokenStream tokens = new CommonTokenStream(lexer);
        CymbolParser parser = new CymbolParser(tokens);
        parser.setBuildParseTree(true);

        ParseTree tree = parser.file();
        // show tree in text form
        System.out.println(tree.toStringTree(parser));

        // Here's another example that uses StringTemplate to generate output
//        System.out.println(collector.graph.toST().render());
    }
}