groovyrecognizer.java

来自「Groovy动态语言 运行在JVM中的动态语言 可以方便的处理业务逻辑变化大的业」· Java 代码 · 共 2,284 行 · 第 1/5 页

// $ANTLR 2.7.2: "groovy.g" -> "GroovyRecognizer.java"$

package org.codehaus.groovy.antlr.parser;
import org.codehaus.groovy.antlr.*;
import java.util.*;
import java.io.InputStream;
import java.io.Reader;
import antlr.InputBuffer;
import antlr.LexerSharedInputState;

import antlr.TokenBuffer;
import antlr.TokenStreamException;
import antlr.TokenStreamIOException;
import antlr.ANTLRException;
import antlr.LLkParser;
import antlr.Token;
import antlr.TokenStream;
import antlr.RecognitionException;
import antlr.NoViableAltException;
import antlr.MismatchedTokenException;
import antlr.SemanticException;
import antlr.ParserSharedInputState;
import antlr.collections.impl.BitSet;
import antlr.collections.AST;
import java.util.Hashtable;
import antlr.ASTFactory;
import antlr.ASTPair;
import antlr.collections.impl.ASTArray;

/** JSR-241 Groovy Recognizer
 *
 * Run 'java Main [-showtree] directory-full-of-groovy-files'
 *
 * [The -showtree option pops up a Swing frame that shows
 *  the AST constructed from the parser.]
 *
 * Contributing authors:
 *              John Mitchell           [e-mail]
 *              Terence Parr            [e-mail]
 *              John Lilley             [e-mail]
 *              Scott Stanchfield       [e-mail]
 *              Markus Mohnen           [e-mail]
 *              Peter Williams          [e-mail]
 *              Allan Jacobs            [e-mail]
 *              Steve Messick           [e-mail]
 *              James Strachan          [e-mail]
 *              John Pybus              [e-mail]
 *              John Rose               [e-mail]
 *              Jeremy Rayner           [e-mail]
 *
 * Version 1.00 December 9, 1997 -- initial release
 * Version 1.01 December 10, 1997
 *              fixed bug in octal def (0..7 not 0..8)
 * Version 1.10 August 1998 (parrt)
 *              added tree construction
 *              fixed definition of WS,comments for mac,pc,unix newlines
 *              added unary plus
 * Version 1.11 (Nov 20, 1998)
 *              Added "shutup" option to turn off last ambig warning.
 *              Fixed inner class def to allow named class defs as statements
 *              synchronized requires compound not simple statement
 *              add [] after builtInType DOT class in primaryExpression
 *              "const" is reserved but not valid..removed from modifiers
 * Version 1.12 (Feb 2, 1999)
 *              Changed LITERAL_xxx to xxx in tree grammar.
 *              Updated java.g to use tokens {...} now for 2.6.0 (new feature).
 *
 * Version 1.13 (Apr 23, 1999)
 *              Didn't have (stat)? for else clause in tree parser.
 *              Didn't gen ASTs for interface extends.  Updated tree parser too.
 *              Updated to 2.6.0.
 * Version 1.14 (Jun 20, 1999)
 *              Allowed final/abstract on local classes.
 *              Removed local interfaces from methods
 *              Put instanceof precedence where it belongs...in relationalExpr
 *                      It also had expr not type as arg; fixed it.
 *              Missing ! on SEMI in classBlock
 *              fixed: (expr) + "string" was parsed incorrectly (+ as unary plus).
 *              fixed: didn't like Object[].class in parser or tree parser
 * Version 1.15 (Jun 26, 1999)
 *              Screwed up rule with instanceof in it. :(  Fixed.
 *              Tree parser didn't like (expr).something; fixed.
 *              Allowed multiple inheritance in tree grammar. oops.
 * Version 1.16 (August 22, 1999)
 *              Extending an interface built a wacky tree: had extra EXTENDS.
 *              Tree grammar didn't allow multiple superinterfaces.
 *              Tree grammar didn't allow empty var initializer: {}
 * Version 1.17 (October 12, 1999)
 *              ESC lexer rule allowed 399 max not 377 max.
 *              java.tree.g didn't handle the expression of synchronized
 *              statements.
 * Version 1.18 (August 12, 2001)
 *              Terence updated to Java 2 Version 1.3 by
 *              observing/combining work of Allan Jacobs and Steve
 *              Messick.  Handles 1.3 src.  Summary:
 *              o  primary didn't include boolean.class kind of thing
 *              o  constructor calls parsed explicitly now:
 *                 see explicitConstructorInvocation
 *              o  add strictfp modifier
 *              o  missing objBlock after new expression in tree grammar
 *              o  merged local class definition alternatives, moved after declaration
 *              o  fixed problem with ClassName.super.field
 *              o  reordered some alternatives to make things more efficient
 *              o  long and double constants were not differentiated from int/float
 *              o  whitespace rule was inefficient: matched only one char
 *              o  add an examples directory with some nasty 1.3 cases
 *              o  made Main.java use buffered IO and a Reader for Unicode support
 *              o  supports UNICODE?
 *                 Using Unicode charVocabulay makes code file big, but only
 *                 in the bitsets at the end. I need to make ANTLR generate
 *                 unicode bitsets more efficiently.
 * Version 1.19 (April 25, 2002)
 *              Terence added in nice fixes by John Pybus concerning floating
 *              constants and problems with super() calls.  John did a nice
 *              reorg of the primary/postfix expression stuff to read better
 *              and makes f.g.super() parse properly (it was METHOD_CALL not
 *              a SUPER_CTOR_CALL).  Also:
 *
 *              o  "finally" clause was a root...made it a child of "try"
 *              o  Added stuff for asserts too for Java 1.4, but *commented out*
 *                 as it is not backward compatible.
 *
 * Version 1.20 (October 27, 2002)
 *
 *        Terence ended up reorging John Pybus' stuff to
 *        remove some nondeterminisms and some syntactic predicates.
 *        Note that the grammar is stricter now; e.g., this(...) must
 *      be the first statement.
 *
 *        Trinary ?: operator wasn't working as array name:
 *                (isBig ? bigDigits : digits)[i];
 *
 *        Checked parser/tree parser on source for
 *                Resin-2.0.5, jive-2.1.1, jdk 1.3.1, Lucene, antlr 2.7.2a4,
 *              and the 110k-line jGuru server source.
 *
 * Version 1.21 (October 17, 2003)
 *  Fixed lots of problems including:
 *  Ray Waldin: add typeDefinition to interfaceBlock in java.tree.g
 *  He found a problem/fix with floating point that start with 0
 *  Ray also fixed problem that (int.class) was not recognized.
 *  Thorsten van Ellen noticed that \n are allowed incorrectly in strings.
 *  TJP fixed CHAR_LITERAL analogously.
 *
 * Version 1.21.2 (March, 2003)
 *        Changes by Matt Quail to support generics (as per JDK1.5/JSR14)
 *        Notes:
 *        o We only allow the "extends" keyword and not the "implements"
 *              keyword, since thats what JSR14 seems to imply.
 *        o Thanks to Monty Zukowski for his help on the antlr-interest
 *              mail list.
 *        o Thanks to Alan Eliasen for testing the grammar over his
 *              Fink source base
 *
 * Version 1.22 (July, 2004)
 *        Changes by Michael Studman to support Java 1.5 language extensions
 *        Notes:
 *        o Added support for annotations types
 *        o Finished off Matt Quail's generics enhancements to support bound type arguments
 *        o Added support for new for statement syntax
 *        o Added support for static import syntax
 *        o Added support for enum types
 *        o Tested against JDK 1.5 source base and source base of jdigraph project
 *        o Thanks to Matt Quail for doing the hard part by doing most of the generics work
 *
 * Version 1.22.1 (July 28, 2004)
 *        Bug/omission fixes for Java 1.5 language support
 *        o Fixed tree structure bug with classOrInterface - thanks to Pieter Vangorpto for
 *              spotting this
 *        o Fixed bug where incorrect handling of SR and BSR tokens would cause type
 *              parameters to be recognised as type arguments.
 *        o Enabled type parameters on constructors, annotations on enum constants
 *              and package definitions
 *        o Fixed problems when parsing if ((char.class.equals(c))) {} - solution by Matt Quail at Cenqua
 *
 * Version 1.22.2 (July 28, 2004)
 *        Slight refactoring of Java 1.5 language support
 *        o Refactored for/"foreach" productions so that original literal "for" literal
 *          is still used but the for sub-clauses vary by token type
 *        o Fixed bug where type parameter was not included in generic constructor's branch of AST
 *
 * Version 1.22.3 (August 26, 2004)
 *        Bug fixes as identified by Michael Stahl; clean up of tabs/spaces
 *        and other refactorings
 *        o Fixed typeParameters omission in identPrimary and newStatement
 *        o Replaced GT reconcilliation code with simple semantic predicate
 *        o Adapted enum/assert keyword checking support from Michael Stahl's java15 grammar
 *        o Refactored typeDefinition production and field productions to reduce duplication
 *
 * Version 1.22.4 (October 21, 2004)
 *    Small bux fixes
 *    o Added typeArguments to explicitConstructorInvocation, e.g. new <String>MyParameterised()
 *    o Added typeArguments to postfixExpression productions for anonymous inner class super
 *      constructor invocation, e.g. new Outer().<String>super()
 *    o Fixed bug in array declarations identified by Geoff Roy
 *
 * Version 1.22.4.g.1
 *    o I have taken java.g for Java1.5 from Michael Studman (1.22.4)
 *      and have applied the groovy.diff from java.g (1.22) by John Rose
 *      back onto the new root (1.22.4) - Jeremy Rayner (Jan 2005)
 *    o for a map of the task see... 
 *      http://groovy.javanicus.com/java-g.png
 *
 * This grammar is in the PUBLIC DOMAIN
 */
public class GroovyRecognizer extends antlr.LLkParser       implements GroovyTokenTypes
 {

        /** This factory is the correct way to wire together a Groovy parser and lexer. */
    public static GroovyRecognizer make(GroovyLexer lexer) {
        GroovyRecognizer parser = new GroovyRecognizer(lexer.plumb());
        // TODO: set up a common error-handling control block, to avoid excessive tangle between these guys
        parser.lexer = lexer;
        lexer.parser = parser;
        parser.setASTNodeClass("org.codehaus.groovy.antlr.GroovySourceAST");
        parser.warningList = new ArrayList();
        return parser;
    }
    // Create a scanner that reads from the input stream passed to us...
    public static GroovyRecognizer make(InputStream in) { return make(new GroovyLexer(in)); }
    public static GroovyRecognizer make(Reader in) { return make(new GroovyLexer(in)); }
    public static GroovyRecognizer make(InputBuffer in) { return make(new GroovyLexer(in)); }
    public static GroovyRecognizer make(LexerSharedInputState in) { return make(new GroovyLexer(in)); }
    
    private static GroovySourceAST dummyVariableToforceClassLoaderToFindASTClass = new GroovySourceAST();

    List warningList;
    public List getWarningList() { return warningList; }
    
    GroovyLexer lexer;
    public GroovyLexer getLexer() { return lexer; }
    public void setFilename(String f) { super.setFilename(f); lexer.setFilename(f); }
    private SourceBuffer sourceBuffer;
    public void setSourceBuffer(SourceBuffer sourceBuffer) {
        this.sourceBuffer = sourceBuffer;
    }

    /** Create an AST node with the token type and text passed in, but
     *  with the same background information as another supplied Token (e.g. line numbers)
     * to be used in place of antlr tree construction syntax,
     * i.e. #[TOKEN,"text"]  becomes  create(TOKEN,"text",anotherToken)
     *
     * todo - change antlr.ASTFactory to do this instead...
     */
    public AST create(int type, String txt, Token first, Token last) {
        AST t = astFactory.create(type,txt);
        if ( t != null && first != null) {
            // first copy details from first token
            t.initialize(first);
            // then ensure that type and txt are specific to this new node
            t.initialize(type,txt);
        }

        if ((t instanceof GroovySourceAST) && last != null) {
            GroovySourceAST node = (GroovySourceAST)t;
            node.setLast(last);
            // This is a good point to call node.setSnippet(),
            // but it bulks up the AST too much for production code.
        }
        return t;
    }


    // stuff to adjust ANTLR's tracing machinery
    public static boolean tracing = false;  // only effective if antlr.Tool is run with -traceParser
    public void traceIn(String rname) throws TokenStreamException {
        if (!GroovyRecognizer.tracing)  return;
        super.traceIn(rname);
    }
    public void traceOut(String rname) throws TokenStreamException {
        if (!GroovyRecognizer.tracing)  return;
        if (returnAST != null)  rname += returnAST.toStringList();
        super.traceOut(rname);
    }
        
    // Error handling.  This is a funnel through which parser errors go, when the parser can suggest a solution.
    public void requireFailed(String problem, String solution) throws SemanticException {
        // TODO: Needs more work.
        Token lt = null;
        try { lt = LT(1); }
        catch (TokenStreamException ee) { }
        if (lt == null)  lt = Token.badToken;
        throw new SemanticException(problem + ";\n   solution: " + solution,
                                    getFilename(), lt.getLine(), lt.getColumn());
    }

    public void addWarning(String warning, String solution) {
        Token lt = null;
        try { lt = LT(1); }
        catch (TokenStreamException ee) { }
        if (lt == null)  lt = Token.badToken;

        Map row = new HashMap();
        row.put("warning" ,warning);
        row.put("solution",solution);
        row.put("filename",getFilename());
        row.put("line"    ,new Integer(lt.getLine()));
        row.put("column"  ,new Integer(lt.getColumn()));
        // System.out.println(row);
        warningList.add(row);
    }

    // Convenience method for checking of expected error syndromes.
    private void require(boolean z, String problem, String solution) throws SemanticException {
        if (!z)  requireFailed(problem, solution);
    }


    // Query a name token to see if it begins with a capital letter.
    // This is used to tell the difference (w/o symbol table access) between {String x} and {println x}.
    private boolean isUpperCase(Token x) {
        if (x == null || x.getType() != IDENT)  return false;  // cannot happen?
        String xtext = x.getText();
        return (xtext.length() > 0 && Character.isUpperCase(xtext.charAt(0)));
    }

    private AST currentClass = null;  // current enclosing class (for constructor recognition)
    // Query a name token to see if it is identical with the current class name.
    // This is used to distinguish constructors from other methods.
    private boolean isConstructorIdent(Token x) {
        if (currentClass == null)  return false;
        if (currentClass.getType() != IDENT)  return false;  // cannot happen?
        String cname = currentClass.getText();

        if (x == null || x.getType() != IDENT)  return false;  // cannot happen?
        return cname.equals(x.getText());
    }

    // Scratch variable for last 'sep' token.
    // Written by the 'sep' rule, read only by immediate callers of 'sep'.
    // (Not entirely clean, but better than a million xx=sep occurrences.)
    private int sepToken = EOF;

    // Scratch variable for last argument list; tells whether there was a label.
    // Written by 'argList' rule, read only by immediate callers of 'argList'.
    private boolean argListHasLabels = false;

    // Scratch variable, holds most recently completed pathExpression.
    // Read only by immediate callers of 'pathExpression' and 'expression'.
    private AST lastPathExpression = null;

    // Inherited attribute pushed into most expression rules.
    // If not zero, it means that the left context of the expression
    // being parsed is a statement boundary or an initializer sign '='.
    // Only such expressions are allowed to reach across newlines
    // to pull in an LCURLY and appended block.
    private final int LC_STMT = 1, LC_INIT = 2;

    /**
     * Counts the number of LT seen in the typeArguments production.
     * It is used in semantic predicates to ensure we have seen
     * enough closing '>' characters; which actually may have been
     * either GT, SR or BSR tokens.
     */
    private int ltCounter = 0;
    
    /* This symbol is used to work around a known ANTLR limitation.
     * In a loop with syntactic predicate, ANTLR needs help knowing
     * that the loop exit is a second alternative.
     * Example usage:  ( (LCURLY)=> block | {ANTLR_LOOP_EXIT}? )*
     * Probably should be an ANTLR RFE.
     */
    ////// Original comment in Java grammar:
    // Unfortunately a syntactic predicate can only select one of
    // multiple alternatives on the same level, not break out of
    // an enclosing loop, which is why this ugly hack (a fake
    // empty alternative with always-false semantic predicate)
    // is necessary.
    private static final boolean ANTLR_LOOP_EXIT = false;

protected GroovyRecognizer(TokenBuffer tokenBuf, int k) {
  super(tokenBuf,k);
  tokenNames = _tokenNames;
  buildTokenTypeASTClassMap();
  astFactory = new ASTFactory(getTokenTypeToASTClassMap());
}

public GroovyRecognizer(TokenBuffer tokenBuf) {
  this(tokenBuf,3);
}

protected GroovyRecognizer(TokenStream lexer, int k) {
  super(lexer,k);
  tokenNames = _tokenNames;
  buildTokenTypeASTClassMap();
  astFactory = new ASTFactory(getTokenTypeToASTClassMap());
}

public GroovyRecognizer(TokenStream lexer) {
  this(lexer,3);
}

public GroovyRecognizer(ParserSharedInputState state) {
  super(state,3);
  tokenNames = _tokenNames;
  buildTokenTypeASTClassMap();
  astFactory = new ASTFactory(getTokenTypeToASTClassMap());
}

	public final void compilationUnit() throws RecognitionException, TokenStreamException {
		
		returnAST = null;
		ASTPair currentAST = new ASTPair();
		AST compilationUnit_AST = null;
		
		{
		switch ( LA(1)) {
		case SH_COMMENT:
		{
			match(SH_COMMENT);
			break;
		}
		case EOF:
		case FINAL:
		case ABSTRACT:
		case STRICTFP:
		case LITERAL_package:
		case LITERAL_import:
		case LITERAL_static:
		case LITERAL_def:
		case AT:
		case IDENT:
		case LBRACK:
		case LPAREN:
		case LITERAL_class:
		case LITERAL_interface:
		case LITERAL_enum:
		case LITERAL_super:
		case LITERAL_void:
		case LITERAL_boolean:
		case LITERAL_byte:
		case LITERAL_char:
		case LITERAL_short:
		case LITERAL_int:
		case LITERAL_float:
		case LITERAL_long:
		case LITERAL_double:
		case LITERAL_any:
		case STAR:
		case LITERAL_private:
		case LITERAL_public:
		case LITERAL_protected:
		case LITERAL_transient:
		case LITERAL_native:
		case LITERAL_threadsafe:
		case LITERAL_synchronized:
		case LITERAL_volatile:
		case LCURLY:
		case SEMI:
		case NLS:
		case LITERAL_this:
		case STRING_LITERAL:
		case LITERAL_if:
		case LITERAL_while:
		case LITERAL_with:
		case LITERAL_switch:
		case LITERAL_for: