javalexer.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 2,127 行 · 第 1/4 页

// $ANTLR 2.7.2: "java.g" -> "JavaLexer.java"$

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

import java.io.InputStream;
import antlr.TokenStreamException;
import antlr.TokenStreamIOException;
import antlr.TokenStreamRecognitionException;
import antlr.CharStreamException;
import antlr.CharStreamIOException;
import antlr.ANTLRException;
import java.io.Reader;
import java.util.Hashtable;
import antlr.CharScanner;
import antlr.InputBuffer;
import antlr.ByteBuffer;
import antlr.CharBuffer;
import antlr.Token;
import antlr.CommonToken;
import antlr.RecognitionException;
import antlr.NoViableAltForCharException;
import antlr.MismatchedCharException;
import antlr.TokenStream;
import antlr.ANTLRHashString;
import antlr.LexerSharedInputState;
import antlr.collections.impl.BitSet;
import antlr.SemanticException;

public class JavaLexer extends antlr.CharScanner implements JavaTokenTypes, TokenStream
 {

    protected static final int SCS_TYPE = 3, SCS_VAL = 4, SCS_LIT = 8, SCS_LIMIT = 16;
    protected static final int SCS_SQ_TYPE = 0, SCS_TQ_TYPE = 1, SCS_RE_TYPE = 2;
    protected int stringCtorState = 0;  // hack string and regexp constructor boundaries
    protected int lastSigTokenType = EOF;  // last returned non-whitespace token

    /** flag for enabling the "assert" keyword */
	private boolean assertEnabled = true;
	/** flag for enabling the "enum" keyword */
	private boolean enumEnabled = true;
    /** flag for including whitespace tokens (for IDE preparsing) */
    private boolean whitespaceIncluded = false;

	/** Enable the "assert" keyword */
	public void enableAssert(boolean shouldEnable) { assertEnabled = shouldEnable; }
	/** Query the "assert" keyword state */
	public boolean isAssertEnabled() { return assertEnabled; }
	/** Enable the "enum" keyword */
	public void enableEnum(boolean shouldEnable) { enumEnabled = shouldEnable; }
	/** Query the "enum" keyword state */
	public boolean isEnumEnabled() { return enumEnabled; }

    /** This is a bit of plumbing which resumes collection of string constructor bodies,
     *  after an embedded expression has been parsed.
     *  Usage:  new JavaRecognizer(new JavaLexer(in).plumb()).
     */
    public TokenStream plumb() {
        return new TokenStream() {
            public Token nextToken() throws TokenStreamException {
                if (stringCtorState >= SCS_LIT) {
                    // This goo is modeled upon the ANTLR code for nextToken:
                    int quoteType = (stringCtorState & SCS_TYPE);
                    stringCtorState = 0;  // get out of this mode, now
                    resetText();
/*                    try {
                        switch (quoteType) {
                        case SCS_SQ_TYPE:
//todo: suitable replacement???     mSTRING_CTOR_END(true, false, false); 
                        	break;
                        case SCS_TQ_TYPE:
//                            mSTRING_CTOR_END(true, false, true); 
                        	break;
                        case SCS_RE_TYPE:
//                            mREGEXP_CTOR_END(true, false); 
                        	break;
                        default:  throw new AssertionError(false);
                        }
                        lastSigTokenType = _returnToken.getType();
                        return _returnToken;
                    }*//* catch (RecognitionException e) {
                        throw new TokenStreamRecognitionException(e);
                    }*/ /*catch (CharStreamException cse) {
                        if ( cse instanceof CharStreamIOException ) {
                            throw new TokenStreamIOException(((CharStreamIOException)cse).io);
                        }
                        else {
                            throw new TokenStreamException(cse.getMessage());
                        }
                    }*/
                }
                Token token = JavaLexer.this.nextToken();
                int lasttype = token.getType();
                if (whitespaceIncluded) {
                    switch (lasttype) {  // filter out insignificant types
                    case WS:
                    case SL_COMMENT:
                    case ML_COMMENT:
                        lasttype = lastSigTokenType;  // back up!
                    }
                }
                lastSigTokenType = lasttype;
                return token;
            }
        };
    }
    
    protected JavaRecognizer parser;  // little-used link; TODO: get rid of
public JavaLexer(InputStream in) {
	this(new ByteBuffer(in));
}
public JavaLexer(Reader in) {
	this(new CharBuffer(in));
}
public JavaLexer(InputBuffer ib) {
	this(new LexerSharedInputState(ib));
}
public JavaLexer(LexerSharedInputState state) {
	super(state);
	caseSensitiveLiterals = true;
	setCaseSensitive(true);
	literals = new Hashtable();
	literals.put(new ANTLRHashString("byte", this), new Integer(79));
	literals.put(new ANTLRHashString("public", this), new Integer(88));
	literals.put(new ANTLRHashString("case", this), new Integer(121));
	literals.put(new ANTLRHashString("short", this), new Integer(81));
	literals.put(new ANTLRHashString("break", this), new Integer(114));
	literals.put(new ANTLRHashString("while", this), new Integer(113));
	literals.put(new ANTLRHashString("new", this), new Integer(157));
	literals.put(new ANTLRHashString("instanceof", this), new Integer(144));
	literals.put(new ANTLRHashString("implements", this), new Integer(106));
	literals.put(new ANTLRHashString("synchronized", this), new Integer(93));
	literals.put(new ANTLRHashString("float", this), new Integer(83));
	literals.put(new ANTLRHashString("package", this), new Integer(61));
	literals.put(new ANTLRHashString("return", this), new Integer(116));
	literals.put(new ANTLRHashString("throw", this), new Integer(118));
	literals.put(new ANTLRHashString("null", this), new Integer(156));
	literals.put(new ANTLRHashString("threadsafe", this), new Integer(92));
	literals.put(new ANTLRHashString("protected", this), new Integer(89));
	literals.put(new ANTLRHashString("class", this), new Integer(101));
	literals.put(new ANTLRHashString("throws", this), new Integer(108));
	literals.put(new ANTLRHashString("strictfp", this), new Integer(40));
	literals.put(new ANTLRHashString("super", this), new Integer(71));
	literals.put(new ANTLRHashString("transient", this), new Integer(90));
	literals.put(new ANTLRHashString("native", this), new Integer(91));
	literals.put(new ANTLRHashString("interface", this), new Integer(102));
	literals.put(new ANTLRHashString("final", this), new Integer(38));
	literals.put(new ANTLRHashString("if", this), new Integer(111));
	literals.put(new ANTLRHashString("double", this), new Integer(85));
	literals.put(new ANTLRHashString("volatile", this), new Integer(94));
	literals.put(new ANTLRHashString("assert", this), new Integer(119));
	literals.put(new ANTLRHashString("catch", this), new Integer(124));
	literals.put(new ANTLRHashString("try", this), new Integer(122));
	literals.put(new ANTLRHashString("enum", this), new Integer(103));
	literals.put(new ANTLRHashString("int", this), new Integer(82));
	literals.put(new ANTLRHashString("for", this), new Integer(120));
	literals.put(new ANTLRHashString("extends", this), new Integer(70));
	literals.put(new ANTLRHashString("boolean", this), new Integer(78));
	literals.put(new ANTLRHashString("char", this), new Integer(80));
	literals.put(new ANTLRHashString("private", this), new Integer(87));
	literals.put(new ANTLRHashString("default", this), new Integer(105));
	literals.put(new ANTLRHashString("false", this), new Integer(155));
	literals.put(new ANTLRHashString("this", this), new Integer(107));
	literals.put(new ANTLRHashString("static", this), new Integer(64));
	literals.put(new ANTLRHashString("abstract", this), new Integer(39));
	literals.put(new ANTLRHashString("continue", this), new Integer(115));
	literals.put(new ANTLRHashString("finally", this), new Integer(123));
	literals.put(new ANTLRHashString("else", this), new Integer(112));
	literals.put(new ANTLRHashString("import", this), new Integer(63));
	literals.put(new ANTLRHashString("void", this), new Integer(77));
	literals.put(new ANTLRHashString("switch", this), new Integer(117));
	literals.put(new ANTLRHashString("true", this), new Integer(154));
	literals.put(new ANTLRHashString("long", this), new Integer(84));
}

public Token nextToken() throws TokenStreamException {
	Token theRetToken=null;
tryAgain:
	for (;;) {
		Token _token = null;
		int _ttype = Token.INVALID_TYPE;
		resetText();
		try {   // for char stream error handling
			try {   // for lexical error handling
				switch ( LA(1)) {
				case '?':
				{
					mQUESTION(true);
					theRetToken=_returnToken;
					break;
				}
				case '(':
				{
					mLPAREN(true);
					theRetToken=_returnToken;
					break;
				}
				case ')':
				{
					mRPAREN(true);
					theRetToken=_returnToken;
					break;
				}
				case '[':
				{
					mLBRACK(true);
					theRetToken=_returnToken;
					break;
				}
				case ']':
				{
					mRBRACK(true);
					theRetToken=_returnToken;
					break;
				}
				case '{':
				{
					mLCURLY(true);
					theRetToken=_returnToken;
					break;
				}
				case '}':
				{
					mRCURLY(true);
					theRetToken=_returnToken;
					break;
				}
				case ':':
				{
					mCOLON(true);
					theRetToken=_returnToken;
					break;
				}
				case ',':
				{
					mCOMMA(true);
					theRetToken=_returnToken;
					break;
				}
				case '~':
				{
					mBNOT(true);
					theRetToken=_returnToken;
					break;
				}
				case ';':
				{
					mSEMI(true);
					theRetToken=_returnToken;
					break;
				}
				case '\t':  case '\n':  case '\u000c':  case '\r':
				case ' ':
				{
					mWS(true);
					theRetToken=_returnToken;
					break;
				}
				case '"':  case '\'':
				{
					mSTRING_LITERAL(true);
					theRetToken=_returnToken;
					break;
				}
				case '$':  case 'A':  case 'B':  case 'C':
				case 'D':  case 'E':  case 'F':  case 'G':
				case 'H':  case 'I':  case 'J':  case 'K':
				case 'L':  case 'M':  case 'N':  case 'O':
				case 'P':  case 'Q':  case 'R':  case 'S':
				case 'T':  case 'U':  case 'V':  case 'W':
				case 'X':  case 'Y':  case 'Z':  case '_':
				case 'a':  case 'b':  case 'c':  case 'd':
				case 'e':  case 'f':  case 'g':  case 'h':
				case 'i':  case 'j':  case 'k':  case 'l':
				case 'm':  case 'n':  case 'o':  case 'p':
				case 'q':  case 'r':  case 's':  case 't':
				case 'u':  case 'v':  case 'w':  case 'x':
				case 'y':  case 'z':
				{
					mIDENT(true);
					theRetToken=_returnToken;
					break;
				}
				case '.':  case '0':  case '1':  case '2':
				case '3':  case '4':  case '5':  case '6':
				case '7':  case '8':  case '9':
				{
					mNUM_INT(true);
					theRetToken=_returnToken;
					break;
				}
				case '@':
				{
					mAT(true);
					theRetToken=_returnToken;
					break;
				}
				default:
					if ((LA(1)=='>') && (LA(2)=='>') && (LA(3)=='>') && (LA(4)=='=')) {
						mBSR_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='>') && (LA(2)=='>') && (LA(3)=='=')) {
						mSR_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='>') && (LA(2)=='>') && (LA(3)=='>') && (true)) {
						mBSR(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='<') && (LA(2)=='<') && (LA(3)=='=')) {
						mSL_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='=') && (LA(2)=='=')) {
						mEQUAL(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='!') && (LA(2)=='=')) {
						mNOT_EQUAL(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='/') && (LA(2)=='=')) {
						mDIV_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='+') && (LA(2)=='=')) {
						mPLUS_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='+') && (LA(2)=='+')) {
						mINC(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='-') && (LA(2)=='=')) {
						mMINUS_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='-') && (LA(2)=='-')) {
						mDEC(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='*') && (LA(2)=='=')) {
						mSTAR_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='%') && (LA(2)=='=')) {
						mMOD_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='>') && (LA(2)=='>') && (true)) {
						mSR(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='>') && (LA(2)=='=')) {
						mGE(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='<') && (LA(2)=='<') && (true)) {
						mSL(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='<') && (LA(2)=='=')) {
						mLE(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='^') && (LA(2)=='=')) {
						mBXOR_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='|') && (LA(2)=='=')) {
						mBOR_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='|') && (LA(2)=='|')) {
						mLOR(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='&') && (LA(2)=='=')) {
						mBAND_ASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='&') && (LA(2)=='&')) {
						mLAND(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='/') && (LA(2)=='/')) {
						mSL_COMMENT(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='/') && (LA(2)=='*')) {
						mML_COMMENT(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='=') && (true)) {
						mASSIGN(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='!') && (true)) {
						mLNOT(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='/') && (true)) {
						mDIV(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='+') && (true)) {
						mPLUS(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='-') && (true)) {
						mMINUS(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='*') && (true)) {
						mSTAR(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='%') && (true)) {
						mMOD(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='>') && (true)) {
						mGT(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='<') && (true)) {
						mLT(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='^') && (true)) {
						mBXOR(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='|') && (true)) {
						mBOR(true);
						theRetToken=_returnToken;
					}
					else if ((LA(1)=='&') && (true)) {
						mBAND(true);
						theRetToken=_returnToken;
					}
				else {
					if (LA(1)==EOF_CHAR) {uponEOF(); _returnToken = makeToken(Token.EOF_TYPE);}
				else {throw new NoViableAltForCharException((char)LA(1), getFilename(), getLine(), getColumn());}
				}
				}
				if ( _returnToken==null ) continue tryAgain; // found SKIP token
				_ttype = _returnToken.getType();
				_returnToken.setType(_ttype);
				return _returnToken;
			}
			catch (RecognitionException e) {
				throw new TokenStreamRecognitionException(e);
			}
		}
		catch (CharStreamException cse) {
			if ( cse instanceof CharStreamIOException ) {
				throw new TokenStreamIOException(((CharStreamIOException)cse).io);
			}
			else {
				throw new TokenStreamException(cse.getMessage());
			}
		}
	}
}

	public final void mQUESTION(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException {
		int _ttype; Token _token=null; int _begin=text.length();
		_ttype = QUESTION;
		int _saveIndex;
		
		match('?');
		if ( _createToken && _token==null && _ttype!=Token.SKIP ) {
			_token = makeToken(_ttype);
			_token.setText(new String(text.getBuffer(), _begin, text.length()-_begin));
		}
		_returnToken = _token;
	}
	
	public final void mLPAREN(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException {
		int _ttype; Token _token=null; int _begin=text.length();
		_ttype = LPAREN;
		int _saveIndex;
		
		match('(');
		if ( _createToken && _token==null && _ttype!=Token.SKIP ) {
			_token = makeToken(_ttype);
			_token.setText(new String(text.getBuffer(), _begin, text.length()-_begin));
		}
		_returnToken = _token;
	}
	
	public final void mRPAREN(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException {
		int _ttype; Token _token=null; int _begin=text.length();
		_ttype = RPAREN;
		int _saveIndex;
		
		match(')');
		if ( _createToken && _token==null && _ttype!=Token.SKIP ) {
			_token = makeToken(_ttype);
			_token.setText(new String(text.getBuffer(), _begin, text.length()-_begin));
		}
		_returnToken = _token;
	}
	
	public final void mLBRACK(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException {
		int _ttype; Token _token=null; int _begin=text.length();
		_ttype = LBRACK;
		int _saveIndex;
		
		match('[');
		if ( _createToken && _token==null && _ttype!=Token.SKIP ) {
			_token = makeToken(_ttype);
			_token.setText(new String(text.getBuffer(), _begin, text.length()-_begin));
		}
		_returnToken = _token;
	}
	
	public final void mRBRACK(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException {
		int _ttype; Token _token=null; int _begin=text.length();
		_ttype = RBRACK;
		int _saveIndex;
		
		match(']');
		if ( _createToken && _token==null && _ttype!=Token.SKIP ) {