Author: abelevich Date: 2008-10-30 06:04:25 -0400 (Thu, 30 Oct 2008) New Revision: 10975 Added: trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextLexer.java trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextParser.java trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextParserTokenTypes.java Log: Html to SeamText parser Added: trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextLexer.java =================================================================== --- trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextLexer.java (rev 0) +++ trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextLexer.java 2008-10-30 10:04:25 UTC (rev 10975) @@ -0,0 +1,808 @@ +// $ANTLR : "html-seamtext.g" -> "HtmlSeamTextLexer.java"$ + + package org.richfaces.antlr; + +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 HtmlSeamTextLexer extends antlr.CharScanner implements HtmlSeamTextParserTokenTypes, TokenStream + { +public HtmlSeamTextLexer(InputStream in) { + this(new ByteBuffer(in)); +} +public HtmlSeamTextLexer(Reader in) { + this(new CharBuffer(in)); +} +public HtmlSeamTextLexer(InputBuffer ib) { + this(new LexerSharedInputState(ib)); +} +public HtmlSeamTextLexer(LexerSharedInputState state) { + super(state); + caseSensitiveLiterals = true; + setCaseSensitive(true); + literals = new Hashtable(); +} + +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 '0': case '1': case '2': case '3': + case '4': case '5': case '6': case '7': + case '8': case '9': 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 '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': + { + mALPHANUMERICWORD(true); + theRetToken=_returnToken; + break; + } + case '!': case '$': case '%': case '(': + case ')': case ',': case '-': case '.': + case ':': case ';': case '?': case '@': + case '{': case '}': + { + mPUNCTUATION(true); + theRetToken=_returnToken; + break; + } + case '=': + { + mEQ(true); + theRetToken=_returnToken; + break; + } + case '+': + { + mPLUS(true); + theRetToken=_returnToken; + break; + } + case '_': + { + mUNDERSCORE(true); + theRetToken=_returnToken; + break; + } + case '*': + { + mSTAR(true); + theRetToken=_returnToken; + break; + } + case '/': + { + mSLASH(true); + theRetToken=_returnToken; + break; + } + case '\\': + { + mESCAPE(true); + theRetToken=_returnToken; + break; + } + case '|': + { + mBAR(true); + theRetToken=_returnToken; + break; + } + case '`': + { + mBACKTICK(true); + theRetToken=_returnToken; + break; + } + case '~': + { + mTWIDDLE(true); + theRetToken=_returnToken; + break; + } + case '"': + { + mDOUBLEQUOTE(true); + theRetToken=_returnToken; + break; + } + case '\'': + { + mSINGLEQUOTE(true); + theRetToken=_returnToken; + break; + } + case '[': + { + mOPEN(true); + theRetToken=_returnToken; + break; + } + case ']': + { + mCLOSE(true); + theRetToken=_returnToken; + break; + } + case '#': + { + mHASH(true); + theRetToken=_returnToken; + break; + } + case '^': + { + mHAT(true); + theRetToken=_returnToken; + break; + } + case '>': + { + mGT(true); + theRetToken=_returnToken; + break; + } + case '<': + { + mLT(true); + theRetToken=_returnToken; + break; + } + case '\t': case ' ': + { + mSPACE(true); + theRetToken=_returnToken; + break; + } + case '\n': case '\r': + { + mNEWLINE(true); + theRetToken=_returnToken; + break; + } + case '\uffff': + { + mEOF(true); + theRetToken=_returnToken; + break; + } + default: + if ((LA(1)=='&') && (LA(2)=='l')) { + mESCAPED_LT(true); + theRetToken=_returnToken; + } + else if ((LA(1)=='&') && (LA(2)=='g')) { + mESCAPED_GT(true); + theRetToken=_returnToken; + } + else if ((LA(1)=='&') && (LA(2)=='a')) { + mESCAPED_AMP(true); + theRetToken=_returnToken; + } + else if ((LA(1)=='&') && (LA(2)=='q')) { + mESCAPED_QOUT(true); + theRetToken=_returnToken; + } + else if ((_tokenSet_0.member(LA(1)))) { + mUNICODEWORD(true); + theRetToken=_returnToken; + } + else if ((LA(1)=='&') && (true)) { + mAMPERSAND(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(); + _ttype = testLiteralsTable(_ttype); + _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 mALPHANUMERICWORD(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = ALPHANUMERICWORD; + int _saveIndex; + + { + int _cnt430=0; + _loop430: + do { + switch ( LA(1)) { + 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': + { + matchRange('a','z'); + break; + } + 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': + { + matchRange('A','Z'); + break; + } + case '0': case '1': case '2': case '3': + case '4': case '5': case '6': case '7': + case '8': case '9': + { + matchRange('0','9'); + break; + } + default: + { + if ( _cnt430>=1 ) { break _loop430; } else {throw new NoViableAltForCharException((char)LA(1), getFilename(), getLine(), getColumn());} + } + } + _cnt430++; + } while (true); + } + 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 mUNICODEWORD(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = UNICODEWORD; + int _saveIndex; + + { + int _cnt433=0; + _loop433: + do { + if (((LA(1) >= '\u00a0' && LA(1) <= '\u00ff'))) { + matchRange('\u00a0','\u00ff'); + } + else if (((LA(1) >= '\u0100' && LA(1) <= '\u017f'))) { + matchRange('\u0100','\u017f'); + } + else if (((LA(1) >= '\u0180' && LA(1) <= '\u024f'))) { + matchRange('\u0180','\u024f'); + } + else if (((LA(1) >= '\u0250' && LA(1) <= '\ufaff'))) { + matchRange('\u0250','\ufaff'); + } + else if (((LA(1) >= '\uff00' && LA(1) <= '\uffef'))) { + matchRange('\uff00','\uffef'); + } + else { + if ( _cnt433>=1 ) { break _loop433; } else {throw new NoViableAltForCharException((char)LA(1), getFilename(), getLine(), getColumn());} + } + + _cnt433++; + } while (true); + } + 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 mPUNCTUATION(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = PUNCTUATION; + int _saveIndex; + + switch ( LA(1)) { + case '-': + { + match('-'); + break; + } + case ';': + { + match(';'); + break; + } + case ':': + { + match(':'); + break; + } + case '(': + { + match('('); + break; + } + case ')': + { + match(')'); + break; + } + case '{': + { + match('{'); + break; + } + case '}': + { + match('}'); + break; + } + case '?': + { + match('?'); + break; + } + case '!': + { + match('!'); + break; + } + case '@': + { + match('@'); + break; + } + case '%': + { + match('%'); + break; + } + case '.': + { + match('.'); + break; + } + case ',': + { + match(','); + break; + } + case '$': + { + match('$'); + break; + } + default: + { + throw new NoViableAltForCharException((char)LA(1), getFilename(), getLine(), getColumn()); + } + } + 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 mEQ(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = EQ; + 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 mPLUS(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = PLUS; + 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 mUNDERSCORE(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = UNDERSCORE; + 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 mSTAR(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = STAR; + 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 mSLASH(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = SLASH; + 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 mESCAPE(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = ESCAPE; + 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 mBAR(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = BAR; + 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 mBACKTICK(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = BACKTICK; + 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 mTWIDDLE(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = TWIDDLE; + 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 mDOUBLEQUOTE(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = DOUBLEQUOTE; + 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 mSINGLEQUOTE(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = SINGLEQUOTE; + 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 mOPEN(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = OPEN; + 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 mCLOSE(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = CLOSE; + 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 mHASH(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = HASH; + 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 mHAT(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = HAT; + 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 mGT(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = GT; + 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 mLT(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = LT; + 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 mAMPERSAND(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = AMPERSAND; + 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 mSPACE(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = SPACE; + int _saveIndex; + + { + int _cnt455=0; + _loop455: + do { + switch ( LA(1)) { + case ' ': + { + match(' '); + break; + } + case '\t': + { + match('\t'); + break; + } + default: + { + if ( _cnt455>=1 ) { break _loop455; } else {throw new NoViableAltForCharException((char)LA(1), getFilename(), getLine(), getColumn());} + } + } + _cnt455++; + } while (true); + } + 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 mNEWLINE(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = NEWLINE; + int _saveIndex; + + if ((LA(1)=='\r') && (LA(2)=='\n')) { + match("\r\n"); + } + else if ((LA(1)=='\r') && (true)) { + match('\r'); + } + else if ((LA(1)=='\n')) { + match('\n'); + } + else { + throw new NoViableAltForCharException((char)LA(1), getFilename(), getLine(), getColumn()); + } + + 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 mEOF(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = Token.EOF_TYPE; + int _saveIndex; + + match('\uFFFF'); + 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 mESCAPED_LT(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = ESCAPED_LT; + int _saveIndex; + + match("&lt;"); + 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 mESCAPED_GT(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = ESCAPED_GT; + int _saveIndex; + + match("&gt;"); + 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 mESCAPED_AMP(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = ESCAPED_AMP; + int _saveIndex; + + match("&amp;"); + 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 mESCAPED_QOUT(boolean _createToken) throws RecognitionException, CharStreamException, TokenStreamException { + int _ttype; Token _token=null; int _begin=text.length(); + _ttype = ESCAPED_QOUT; + int _saveIndex; + + match("&quot;"); + if ( _createToken && _token==null && _ttype!=Token.SKIP ) { + _token = makeToken(_ttype); + _token.setText(new String(text.getBuffer(), _begin, text.length()-_begin)); + } + _returnToken = _token; + } + + + private static final long[] mk_tokenSet_0() { + long[] data = new long[4084]; + data[2]=-4294967296L; + for (int i = 3; i<=1003; i++) { data[i]=-1L; } + for (int i = 1020; i<=1022; i++) { data[i]=-1L; } + data[1023]=281474976710655L; + return data; + } + public static final BitSet _tokenSet_0 = new BitSet(mk_tokenSet_0()); + + } Added: trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextParser.java =================================================================== --- trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextParser.java (rev 0) +++ trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextParser.java 2008-10-30 10:04:25 UTC (rev 10975) @@ -0,0 +1,1581 @@ +// $ANTLR : "html-seamtext.g" -> "HtmlSeamTextParser.java"$ + + package org.richfaces.antlr; + +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; + +public class HtmlSeamTextParser extends antlr.LLkParser implements HtmlSeamTextParserTokenTypes + { + + public class HtmlRecognitionException extends RecognitionException { + Token openingElement; + RecognitionException wrappedException; + + public HtmlRecognitionException(Token openingElement, RecognitionException wrappedException) { + this.openingElement = openingElement; + this.wrappedException = wrappedException; + } + + public Token getOpeningElement() { + return openingElement; + } + + public String getMessage() { + return wrappedException.getMessage(); + } + + public Throwable getCause() { + return wrappedException; + } + } + + + public interface Sanitizer { + + public void validateLinkTagURI(Token element, String uri) throws SemanticException; + public void validateHtmlElement(Token element) throws SemanticException; + public void validateHtmlAttribute(Token element, Token attribute) throws SemanticException; + public void validateHtmlAttributeValue(Token element, Token attribute, String attributeValue) throws SemanticException; + public void escapeSeamTextToken(Token element); + public String getInvalidURIMessage(String uri); + public String getInvalidElementMessage(String elementName); + public String getInvalidAttributeMessage(String elementName, String attributeName); + public String getInvalidAttributeValueMessage(String elementName, String attributeName, String value); + + } + + public static class DefaultSanitizer implements HtmlSeamTextParser.Sanitizer { + + protected java.util.Set<String> attributesWhoseValueIsAURI = new java.util.HashSet(java.util.Arrays.asList( + "action", "cite", "href", "longdesc", "src", "xlink:href", "xml:base" + )); + + + protected java.util.Set<String> uriSchemes = new java.util.HashSet(java.util.Arrays.asList( + "afs", "aim", "callto", "ed2k", "feed", "ftp", "gopher", "http", "https", + "irc", "mailto", "news", "nntp", "rsync", "rtsp", "sftp", "ssh", "tag", + "tel", "telnet", "urn", "webcal", "wtai", "xmpp" + )); + + protected java.util.Set<String> acceptableElements = new java.util.HashSet(java.util.Arrays.asList( + "a", "abbr", "acronym", "address", "area", "b", "bdo", "big", "blockquote", + "br", "button", "caption", "center", "cite", "code", "col", "colgroup", "dd", + "del", "dfn", "dir", "div", "dl", "dt", "em", "fieldset", "font", "form", + "h1", "h2", "h3", "h4", "h5", "h6", "hr", "i", "img", "input", "ins", "kbd", + "label", "legend", "li", "map", "menu", "ol", "optgroup", "option", "p", + "pre", "q", "s", "samp", "select", "small", "span", "strike", "strong", + "sub", "sup", "table", "tbody", "td", "textarea", "tfoot", "th", "thead", + "tr", "tt", "u", "ul", "var", "wbr" + )); + + protected java.util.Set<String> mathmlElements = new java.util.HashSet(java.util.Arrays.asList( + "maction", "math", "merror", "mfrac", "mi", "mmultiscripts", "mn", "mo", + "mover", "mpadded", "mphantom", "mprescripts", "mroot", "mrow", "mspace", + "msqrt", "mstyle", "msub", "msubsup", "msup", "mtable", "mtd", "mtext", + "mtr", "munder", "munderover", "none" + )); + + protected java.util.Set<String> svgElements = new java.util.HashSet(java.util.Arrays.asList( + "a", "animate", "animateColor", "animateMotion", "animateTransform", + "circle", "defs", "desc", "ellipse", "font-face", "font-face-name", + "font-face-src", "g", "glyph", "hkern", "image", "line", "linearGradient", + "marker", "metadata", "missing-glyph", "mpath", "path", "polygon", + "polyline", "radialGradient", "rect", "set", "stop", "svg", "switch", "text", + "title", "tspan", "use" + )); + + protected java.util.Set<String> acceptableAttributes = new java.util.HashSet(java.util.Arrays.asList( + "abbr", "accept", "accept-charset", "accesskey", "action", "align", "alt", + "axis", "border", "cellpadding", "cellspacing", "char", "charoff", "charset", + "checked", "cite", "class", "clear", "color", "cols", "colspan", "compact", + "coords", "datetime", "dir", "disabled", "enctype", "for", "frame", + "headers", "height", "href", "hreflang", "hspace", "id", "ismap", "label", + "lang", "longdesc", "maxlength", "media", "method", "multiple", "name", + "nohref", "noshade", "nowrap", "prompt", "readonly", "rel", "rev", "rows", + "rowspan", "rules", "scope", "selected", "shape", "size", "span", "src", + "start", "style", "summary", "tabindex", "target", "title", "type", "usemap", + "valign", "value", "vspace", "width", "xml:lang" + )); + + protected java.util.Set<String> mathmlAttributes = new java.util.HashSet(java.util.Arrays.asList( + "actiontype", "align", "columnalign", "columnalign", "columnalign", + "columnlines", "columnspacing", "columnspan", "depth", "display", + "displaystyle", "equalcolumns", "equalrows", "fence", "fontstyle", + "fontweight", "frame", "height", "linethickness", "lspace", "mathbackground", + "mathcolor", "mathvariant", "mathvariant", "maxsize", "minsize", "other", + "rowalign", "rowalign", "rowalign", "rowlines", "rowspacing", "rowspan", + "rspace", "scriptlevel", "selection", "separator", "stretchy", "width", + "width", "xlink:href", "xlink:show", "xlink:type", "xmlns", "xmlns:xlink" + )); + + + protected java.util.Set<String> svgAttributes = new java.util.HashSet(java.util.Arrays.asList( + "accent-height", "accumulate", "additive", "alphabetic", "arabic-form", + "ascent", "attributeName", "attributeType", "baseProfile", "bbox", "begin", + "by", "calcMode", "cap-height", "class", "color", "color-rendering", + "content", "cx", "cy", "d", "descent", "display", "dur", "dx", "dy", "end", + "fill", "fill-rule", "font-family", "font-size", "font-stretch", + "font-style", "font-variant", "font-weight", "from", "fx", "fy", "g1", "g2", + "glyph-name", "gradientUnits", "hanging", "height", "horiz-adv-x", + "horiz-origin-x", "id", "ideographic", "k", "keyPoints", "keySplines", + "keyTimes", "lang", "marker-end", "marker-mid", "marker-start", + "markerHeight", "markerUnits", "markerWidth", "mathematical", "max", "min", + "name", "offset", "opacity", "orient", "origin", "overline-position", + "overline-thickness", "panose-1", "path", "pathLength", "points", + "preserveAspectRatio", "r", "refX", "refY", "repeatCount", "repeatDur", + "requiredExtensions", "requiredFeatures", "restart", "rotate", "rx", "ry", + "slope", "stemh", "stemv", "stop-color", "stop-opacity", + "strikethrough-position", "strikethrough-thickness", "stroke", + "stroke-dasharray", "stroke-dashoffset", "stroke-linecap", "stroke-linejoin", + "stroke-miterlimit", "stroke-opacity", "stroke-width", "systemLanguage", + "target", "text-anchor", "to", "transform", "type", "u1", "u2", + "underline-position", "underline-thickness", "unicode", "unicode-range", + "units-per-em", "values", "version", "viewBox", "visibility", "width", + "widths", "x", "x-height", "x1", "x2", "xlink:actuate", "xlink:arcrole", + "xlink:href", "xlink:role", "xlink:show", "xlink:title", "xlink:type", + "xml:base", "xml:lang", "xml:space", "xmlns", "xmlns:xlink", "y", "y1", "y2", + "zoomAndPan" + )); + + public final java.util.regex.Pattern REGEX_VALID_CSS_VALUE = java.util.regex.Pattern.compile( + "^(#[0-9a-f]{3,6}|rgb\\(\\d{1,3}%?,\\d{1,3}%?,?\\d{1,3}%?\\)?|-?\\d{0,2}\\.?\\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\\))?)$" + ); + + public final java.util.regex.Pattern REGEX_VALID_CSS_STRING1 = java.util.regex.Pattern.compile( + "^([-:,;#%.\\sa-zA-Z0-9!]|\\w-\\w|'[\\s\\w]+'|\"[\\s\\w]+\"|\\([\\d,\\s]+\\))*$" + ); + + public final java.util.regex.Pattern REGEX_VALID_CSS_STRING2 = java.util.regex.Pattern.compile( + "^(\\s*[-\\w]+\\s*:\\s*[^:;]*(;|$))*$" + ); + + + protected java.util.Set<String> styleProperties = new java.util.HashSet(java.util.Arrays.asList( + "azimuth", + "background", "background-attachment", "background-color", "background-image", + "background-position", "background-repeat", + "border", "border-bottom", "border-bottom-color", "border-bottom-style", + "border-bottom-width", "border-collapse", "border-color", "border-left", + "border-left-color", "border-left-style", "border-left-width", "border-right", + "border-right-color", "border-right-style", "border-right-width", "border-spacing", + "border-style", "border-top", "border-top-color", "border-top-style", + "border-top-width", "border-width", + "clear", "color", + "cursor", "direction", "display", "elevation", "float", "font", + "font-family", "font-size", "font-style", "font-variant", "font-weight", + "height", "letter-spacing", "line-height", + "margin", "margin-bottom", "margin-left", "margin-right", "margin-top", + "max-height", "max-width", "min-height", "min-width", + "overflow", + "padding", "padding-bottom", "padding-left", "padding-right", "padding-top", + "pause", "pause-after", "pause-before", "pitch", + "pitch-range", "richness", "speak", "speak-header", "speak-numeral", + "speak-punctuation", "speech-rate", "stress", "text-align", + "text-decoration", "text-indent", "unicode-bidi", "vertical-align", + "voice-family", "volume", "white-space", "width" + )); + + + protected java.util.Set<String> stylePropertiesValues = new java.util.HashSet(java.util.Arrays.asList( + "aqua", "auto", "baseline", "black", "block", "blue", "bold", "both", "bottom", "brown", + "center", "collapse", "dashed", "dotted", "fuchsia", "gray", "green", + "inherit", "italic", "left", "length", "lime", "maroon", "medium", "middle", "navy", "none", "normal", + "nowrap", "olive", "percentage", "pointer", "purple", "red", "right", "silver", "solid", "sub", "super", + "teal", "text-bottom", "text-top", "top", "transparent", "underline", "white", "yellow" + )); + + protected java.util.Set<String> svgStyleProperties = new java.util.HashSet(java.util.Arrays.asList( + "fill", "fill-opacity", "fill-rule", "stroke", "stroke-linecap", + "stroke-linejoin", "stroke-opacity", "stroke-width" + )); + + + public void validateLinkTagURI(Token element, String uri) throws SemanticException { + if (!validateURI(uri)) { + throw createSemanticException("Invalid URI", element); + } + } + + public void validateHtmlElement(Token element) throws SemanticException { + String elementName = element.getText().toLowerCase(); + if (!acceptableElements.contains(elementName) && + !svgElements.contains(elementName) && + !mathmlElements.contains(elementName)) { + throw createSemanticException(getInvalidElementMessage(elementName), element); + } + } + + public void validateHtmlAttribute(Token element, Token attribute) throws SemanticException { + String elementName = element.getText().toLowerCase(); + String attributeName = attribute.getText().toLowerCase(); + if (!acceptableAttributes.contains(attributeName) && + !svgAttributes.contains(attributeName) && + !mathmlAttributes.contains(attributeName)) { + throw createSemanticException(getInvalidAttributeMessage(elementName, attributeName), element); + } + + } + + public void validateHtmlAttributeValue(Token element, Token attribute, String attributeValue) throws SemanticException{ + + if (attributeValue == null || attributeValue.length() == 0) return; + + String elementName = element.getText().toLowerCase(); + String attributeName = attribute.getText().toLowerCase(); + + // Check element with attribute that has URI value (href, src, etc.) + if (attributesWhoseValueIsAURI.contains(attributeName) && !validateURI(attributeValue)) { + throw createSemanticException(getInvalidURIMessage(attributeValue), element); + } + + // Check attribute value of style (CSS filtering) + if (attributeName.equals("style")) { + if (!REGEX_VALID_CSS_STRING1.matcher(attributeValue).matches() || + !REGEX_VALID_CSS_STRING2.matcher(attributeValue).matches()) { + throw createSemanticException( + getInvalidAttributeValueMessage(elementName, attributeName, attributeValue), + element + ); + } + + String[] cssProperties = attributeValue.split(";"); + for (String cssProperty : cssProperties) { + if (!cssProperty.contains(":")) { + throw createSemanticException( + getInvalidAttributeValueMessage(elementName, attributeName, attributeValue), + element + ); + } + String[] property = cssProperty.split(":"); + String propertyName = property[0].trim(); + String propertyValue = property.length == 2 ? property[1].trim() : null; + + // CSS property name + if (!styleProperties.contains(propertyName) && + !svgStyleProperties.contains(propertyName)) { + throw createSemanticException( + getInvalidAttributeValueMessage(elementName, attributeName, attributeValue), + element + ); + } + + // CSS property value + if (propertyValue != null && !stylePropertiesValues.contains(propertyValue)) { + // Not in list, now check the regex + if (!REGEX_VALID_CSS_VALUE.matcher(propertyValue).matches()) { + throw createSemanticException( + getInvalidAttributeValueMessage(elementName, attributeName, attributeValue), + element + ); + } + } + } + } + + + } + + public String getInvalidURIMessage(String uri){ + return "invalid URI"; + } + + public String getInvalidElementMessage(String elementName){ + return "invalid element '" + elementName + "'"; + } + + public String getInvalidAttributeMessage(String elementName, String attributeName){ + return "invalid attribute '" + attributeName + "' for element '" + elementName + "'"; + } + + public String getInvalidAttributeValueMessage(String elementName, String attributeName, String value){ + return "invalid value of attribute '" + attributeName + "' for element '" + elementName + "'"; + } + + public void escapeSeamTextToken(Token element) { + } + + protected boolean validateURI(String uri) { + + // Relative URI starts with a slash + if (uri.startsWith("/")) return true; + + java.net.URI parsedURI; + try { + parsedURI = new java.net.URI(uri); + } catch (java.net.URISyntaxException ex) { + return false; + } + + if (!uriSchemes.contains(parsedURI.getScheme())) { + return false; + } + return true; + } + + public SemanticException createSemanticException(String message, Token element) { + return new SemanticException( + message, + element.getFilename(), element.getLine(), element.getColumn() + ); + } + + } + + + private final String SEAMTEXT_MONOSPACE = "|"; + + private final String SEAMTEXT_TWIDDLE = "~"; + + private final String SEAMTEXT_HASH = "#"; + + private final String SEAMTEXT_HAT = "^"; + + private final String SEAMTEXT_PLUS = "+"; + + private final String SEAMTEXT_STAR = "*"; + + private final String SEAMTEXT_UNDERSCORE = "_"; + + private final String SEAMTEXT_EQ = "="; + + private final String SEAMTEXT_BACKTICK = "`"; + + private final String SEAMTEXT_PARAGRAPH = "\n\n"; + + private final String SEAM_DOUBLEQUOTE = "\""; + + private final String SEAM_OPEN = "["; + + private final String SEAM_CLOSE = "]"; + + private final String SEAM_GT = ">"; + + + protected java.util.Set<String> seamTextSymbols = new java.util.HashSet(java.util.Arrays.asList( + SEAMTEXT_MONOSPACE, SEAMTEXT_TWIDDLE, SEAMTEXT_HASH, SEAMTEXT_HAT, SEAMTEXT_PLUS, SEAMTEXT_STAR, + SEAMTEXT_UNDERSCORE, SEAMTEXT_EQ, SEAMTEXT_BACKTICK, SEAMTEXT_PARAGRAPH, SEAM_DOUBLEQUOTE, SEAM_OPEN, + SEAM_CLOSE, SEAM_GT + )); + + protected java.util.Set<String> htmlSeamTextElements = new java.util.HashSet(java.util.Arrays.asList( + "del", "sup", "pre","p", "q" ,"h1" ,"h2" ,"h3" ,"h4" ,"ul" ,"ol" ,"li" ,"i" ,"tt" ,"u" ,"a")); + + private Sanitizer sanitizer = new DefaultSanitizer(); + + private java.util.Stack<Token> htmlElementStack = new java.util.Stack<Token>(); + + private StringBuilder mainBuilder = new StringBuilder(); + + private StringBuilder linkValueCollector = new StringBuilder(); + + private String linkHolder; + + private StringBuilder builder = mainBuilder; + + + public void setSanitizer(Sanitizer sanitizer) { + this.sanitizer = sanitizer; + } + + public String toString() { + return builder.toString(); + } + + private void beginCapture() { + builder = new StringBuilder(); + } + + private String endCapture() { + String result = builder.toString(); + builder = mainBuilder; + return result; + } + + private void append(String... strings) { + for (String string: strings) builder.append(string); + } + + + public boolean isLink(Token token) { + String name = token.getText().toLowerCase(); + return "a".equals(name); + } + + private String createSeamTextLink(String link, String value) { + + StringBuilder builder = new StringBuilder(); + builder.append("["); + + if (value != null) { + builder.append(value.trim()); + } + + builder.append("=>"); + builder.append(link); + builder.append("]"); + + return builder.toString(); + + } + + public boolean isHeader(Token token) { + String name = token.getText().toLowerCase(); + return ("h1".equals(name) || "h2".equals(name) || "h3".equals(name) || "h4".equals(name)); + } + + public String createSeamTextHeader(Token token) throws SemanticException { + + String name = token.getText(); + StringBuilder seamHeader = new StringBuilder(); + + if("h1".equals(name)) { + seamHeader.append("\n").append(SEAMTEXT_PLUS); + } else if("h2".equals(name)) { + seamHeader.append("\n").append(SEAMTEXT_PLUS).append(SEAMTEXT_PLUS); + } else if("h3".equals(name)) { + seamHeader.append("\n").append(SEAMTEXT_PLUS).append(SEAMTEXT_PLUS).append(SEAMTEXT_PLUS); + } else if("h4".equals(name)) { + seamHeader.append("\n").append(SEAMTEXT_PLUS).append(SEAMTEXT_PLUS).append(SEAMTEXT_PLUS).append(SEAMTEXT_PLUS); + } + + return seamHeader.toString(); + } + + public boolean isList(Token token){ + String name = token.getText(); + return ("ul".equals(name) || "ol".equals(name)); + } + + public boolean isListItem(Token token) { + String name = token.getText().toLowerCase(); + return "li".equals(name); + } + + public String createSeamTextList(Token token, java.util.Stack <Token> htmlElementStack) throws SemanticException { + String seamText = null; + + Token parent = htmlElementStack.peek(); + String parentName = parent.getText().toLowerCase(); + if(parentName.equals("ul")) { + seamText = SEAMTEXT_HASH; + } else if (parentName.equals("ol")){ + seamText = SEAMTEXT_EQ; + } else { + String message = "<li> must follow <ol> or <ul> not <" + parent.getText() + ">"; + throw new SemanticException( message, parent.getFilename(), parent.getLine(), parent.getColumn()); + } + + return seamText != null ? seamText : ""; + } + + // validate lists and headers' + public void validateNestedMarkup(Token name, java.util.Stack <Token> htmlElementStack) throws SemanticException { + if(!htmlElementStack.isEmpty()) { + for(Token token : htmlElementStack) { + + if(token.getText().equals("h1") || token.getText().equals("h2") || token.getText().equals("h3") + || token.getText().equals("h4") || token.getText().equals("ol") || token.getText().equals("ul")) { + String message = "<" + token.getText() + "> contains nested <" + name.getText() + "> token"; + throw new SemanticException( message, name.getFilename(), name.getLine(), name.getColumn()); + } + } + } + + } + + public void validateHeaderMarkup(Token token, java.util.Stack <Token> htmlElementStack) throws TokenStreamException, SemanticException{ + int EOF = 1; + int ALPHANUMERICWORD = 4; + int i = 0; + int type; + + boolean containText = false; + + Token element = htmlElementStack.peek(); + String header = element.getText(); + + if (header.equals("h1") || header.equals("h2") || header.equals("h3") || header.equals("h4")) { + do { + i++; + type = LT(i).getType(); + if (type == ALPHANUMERICWORD) { + containText = true; + break; + } + + } while ( type != EOF); + + if (!containText) { + String message = "You must have some text following a heading"; + throw new SemanticException( message, element.getFilename(), element.getLine(), element.getColumn()); + } + } + + } + + public String createSimpleSeamText(Token token) throws SemanticException{ + + String name = token.getText().toLowerCase(); + StringBuilder seamText = new StringBuilder(); + + if("tt".equals(name)) { + seamText.append(SEAMTEXT_MONOSPACE); + } else if("del".equals(name)) { + seamText.append(SEAMTEXT_TWIDDLE); + } else if("i".equals(name)) { + seamText.append(SEAMTEXT_STAR); + } else if("sup".equals(name)) { + seamText.append(SEAMTEXT_HAT); + } else if("u".equals(name)) { + seamText.append(SEAMTEXT_UNDERSCORE); + } else if("pre".equals(name)) { + seamText.append(SEAMTEXT_BACKTICK); + } else if("p".equals(name)) { + seamText.append(SEAMTEXT_PARAGRAPH); + } else if("q".equals(name)) { + seamText.append(SEAM_DOUBLEQUOTE); + } else if("blockquote".equals(name)) { + seamText.append(SEAM_DOUBLEQUOTE); + } + + return seamText.toString(); + + } + + public boolean isSeamTextElement(Token element){ + String name = element.getText().toLowerCase(); + return htmlSeamTextElements.contains(name); + } + + + public String escapeSeamText(Token token, java.util.Stack <Token> parentHtmlTokens) throws TokenStreamException { + + StringBuilder result = new StringBuilder(); + String tokenName = token.getText(); + + if(parentHtmlTokens != null && !parentHtmlTokens.isEmpty()){ + Token parentToken = parentHtmlTokens.peek(); + String parentTokenName = parentToken.getText().toLowerCase(); + + if ("tt".equals(parentTokenName) || "pre".equals(parentTokenName)) { + + if ("&lt;".equals(tokenName)) { + result.append("<"); + } else if("&amp;".equals(tokenName)) { + result.append("&"); + } else if ("&gt;".equals(tokenName)) { + result.append(">"); + } else if("&quot;".equals(tokenName)){ + result.append("\""); + }else if(seamTextSymbols.contains(tokenName)) { + result.append(tokenName); + } + } + } + result = result.length() != 0 ? result : result.append("\\").append(tokenName); + return result.toString(); + } + + + + +protected HtmlSeamTextParser(TokenBuffer tokenBuf, int k) { + super(tokenBuf,k); + tokenNames = _tokenNames; +} + +public HtmlSeamTextParser(TokenBuffer tokenBuf) { + this(tokenBuf,4); +} + +protected HtmlSeamTextParser(TokenStream lexer, int k) { + super(lexer,k); + tokenNames = _tokenNames; +} + +public HtmlSeamTextParser(TokenStream lexer) { + this(lexer,4); +} + +public HtmlSeamTextParser(ParserSharedInputState state) { + super(state,4); + tokenNames = _tokenNames; +} + + public final void startRule() throws RecognitionException, TokenStreamException { + + + { + _loop388: + do { + if ((LA(1)==NEWLINE)) { + newline(); + } + else { + break _loop388; + } + + } while (true); + } + { + switch ( LA(1)) { + case ALPHANUMERICWORD: + case UNICODEWORD: + case DOUBLEQUOTE: + case ESCAPED_LT: + case ESCAPED_GT: + case ESCAPED_AMP: + case ESCAPED_QOUT: + case PUNCTUATION: + case SINGLEQUOTE: + case SLASH: + case STAR: + case BAR: + case HAT: + case PLUS: + case EQ: + case HASH: + case ESCAPE: + case TWIDDLE: + case OPEN: + case CLOSE: + case BACKTICK: + case GT: + case SPACE: + case LT: + { + text(); + eof(); + break; + } + case EOF: + { + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + } + + public final void newline() throws RecognitionException, TokenStreamException { + + Token n = null; + + n = LT(1); + match(NEWLINE); + append(n.getText()); + } + + public final void text() throws RecognitionException, TokenStreamException { + + + { + int _cnt395=0; + _loop395: + do { + if ((_tokenSet_0.member(LA(1)))) { + { + switch ( LA(1)) { + case STAR: + case BAR: + case HAT: + case PLUS: + case EQ: + case HASH: + case ESCAPE: + case TWIDDLE: + case OPEN: + case CLOSE: + case BACKTICK: + case GT: + { + seamCharacters(); + break; + } + case ALPHANUMERICWORD: + case UNICODEWORD: + case PUNCTUATION: + case SINGLEQUOTE: + case SLASH: + case SPACE: + { + plain(); + break; + } + case LT: + { + html(); + break; + } + case DOUBLEQUOTE: + case ESCAPED_LT: + case ESCAPED_GT: + case ESCAPED_AMP: + case ESCAPED_QOUT: + { + htmlSpecialChars(); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + { + _loop394: + do { + if ((LA(1)==NEWLINE)) { + newline(); + } + else { + break _loop394; + } + + } while (true); + } + } + else { + if ( _cnt395>=1 ) { break _loop395; } else {throw new NoViableAltException(LT(1), getFilename());} + } + + _cnt395++; + } while (true); + } + } + + public final void eof() throws RecognitionException, TokenStreamException { + + + match(Token.EOF_TYPE); + } + + public final void seamCharacters() throws RecognitionException, TokenStreamException { + + Token hat = null; + Token hash = null; + Token open = null; + Token close = null; + Token twiddle = null; + Token bar = null; + Token eq = null; + Token plus = null; + Token backtick = null; + Token st = null; + Token e = null; + Token gt = null; + + switch ( LA(1)) { + case HAT: + { + hat = LT(1); + match(HAT); + append(escapeSeamText(hat, htmlElementStack)); + break; + } + case HASH: + { + hash = LT(1); + match(HASH); + append(escapeSeamText(hash, htmlElementStack)); + break; + } + case OPEN: + { + open = LT(1); + match(OPEN); + append(escapeSeamText(open, htmlElementStack)) ; + break; + } + case CLOSE: + { + close = LT(1); + match(CLOSE); + append(escapeSeamText(close, htmlElementStack)); + break; + } + case TWIDDLE: + { + twiddle = LT(1); + match(TWIDDLE); + append(escapeSeamText(twiddle, htmlElementStack)); + break; + } + case BAR: + { + bar = LT(1); + match(BAR); + append(escapeSeamText(bar, htmlElementStack)); + break; + } + case EQ: + { + eq = LT(1); + match(EQ); + append(escapeSeamText(eq, htmlElementStack)); + break; + } + case PLUS: + { + plus = LT(1); + match(PLUS); + append(escapeSeamText(plus, htmlElementStack)); + break; + } + case BACKTICK: + { + backtick = LT(1); + match(BACKTICK); + append(escapeSeamText(backtick, htmlElementStack)); + break; + } + case STAR: + { + st = LT(1); + match(STAR); + append(escapeSeamText(st, htmlElementStack)); + break; + } + case ESCAPE: + { + e = LT(1); + match(ESCAPE); + append(escapeSeamText(e, htmlElementStack)); + break; + } + case GT: + { + gt = LT(1); + match(GT); + append(escapeSeamText(gt, htmlElementStack)); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + + public final void plain() throws RecognitionException, TokenStreamException { + + + { + switch ( LA(1)) { + case ALPHANUMERICWORD: + case UNICODEWORD: + { + word(); + break; + } + case PUNCTUATION: + case SINGLEQUOTE: + case SLASH: + { + punctuation(); + break; + } + case SPACE: + { + space(); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + } + + public final void html() throws RecognitionException, TokenStreamException { + + + openTag(); + { + _loop407: + do { + if ((LA(1)==SPACE) && (LA(2)==SLASH||LA(2)==GT||LA(2)==SPACE)) { + space(); + } + else if ((LA(1)==SPACE) && (LA(2)==ALPHANUMERICWORD)) { + space(); + attribute(); + } + else { + break _loop407; + } + + } while (true); + } + { + switch ( LA(1)) { + case GT: + { + { + beforeBody(); + body(); + closeTagWithBody(); + } + break; + } + case SLASH: + { + closeTagWithNoBody(); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + } + + public final void htmlSpecialChars() throws RecognitionException, TokenStreamException { + + Token lt = null; + Token gt = null; + Token amp = null; + Token qout = null; + + switch ( LA(1)) { + case DOUBLEQUOTE: + { + match(DOUBLEQUOTE); + append("\""); + break; + } + case ESCAPED_LT: + { + lt = LT(1); + match(ESCAPED_LT); + append(escapeSeamText(lt, htmlElementStack)); + break; + } + case ESCAPED_GT: + { + gt = LT(1); + match(ESCAPED_GT); + append(escapeSeamText(gt, htmlElementStack)); + break; + } + case ESCAPED_AMP: + { + amp = LT(1); + match(ESCAPED_AMP); + append(escapeSeamText(amp, htmlElementStack)); + break; + } + case ESCAPED_QOUT: + { + qout = LT(1); + match(ESCAPED_QOUT); + append(escapeSeamText(qout, htmlElementStack)); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + + public final void word() throws RecognitionException, TokenStreamException { + + Token an = null; + Token uc = null; + + switch ( LA(1)) { + case ALPHANUMERICWORD: + { + an = LT(1); + match(ALPHANUMERICWORD); + append( an.getText() ); + break; + } + case UNICODEWORD: + { + uc = LT(1); + match(UNICODEWORD); + append( uc.getText() ); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + + public final void punctuation() throws RecognitionException, TokenStreamException { + + Token p = null; + Token sq = null; + Token s = null; + + switch ( LA(1)) { + case PUNCTUATION: + { + p = LT(1); + match(PUNCTUATION); + append( p.getText() ); + break; + } + case SINGLEQUOTE: + { + sq = LT(1); + match(SINGLEQUOTE); + append( sq.getText() ); + break; + } + case SLASH: + { + s = LT(1); + match(SLASH); + append( s.getText() ); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + + public final void specialChars() throws RecognitionException, TokenStreamException { + + Token st = null; + Token b = null; + Token h = null; + Token p = null; + Token eq = null; + Token hh = null; + Token e = null; + Token t = null; + Token u = null; + + switch ( LA(1)) { + case STAR: + { + st = LT(1); + match(STAR); + append( st.getText() ); + break; + } + case BAR: + { + b = LT(1); + match(BAR); + append( b.getText() ); + break; + } + case HAT: + { + h = LT(1); + match(HAT); + append( h.getText() ); + break; + } + case PLUS: + { + p = LT(1); + match(PLUS); + append( p.getText() ); + break; + } + case EQ: + { + eq = LT(1); + match(EQ); + append( eq.getText() ); + break; + } + case HASH: + { + hh = LT(1); + match(HASH); + append( hh.getText() ); + break; + } + case ESCAPE: + { + e = LT(1); + match(ESCAPE); + append( e.getText() ); + break; + } + case TWIDDLE: + { + t = LT(1); + match(TWIDDLE); + append( t.getText() ); + break; + } + case UNDERSCORE: + { + u = LT(1); + match(UNDERSCORE); + append( u.getText() ); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + + public final void space() throws RecognitionException, TokenStreamException { + + Token s = null; + + s = LT(1); + match(SPACE); + + + if(!htmlElementStack.isEmpty()) { + String tokenName = htmlElementStack.peek().getText(); + if(!("ul".equals(tokenName) || "ol".equals(tokenName))) { + append(s.getText()); + } + + } else { + append(s.getText()); + } + + + } + + public final void newlineOrEof() throws RecognitionException, TokenStreamException { + + + switch ( LA(1)) { + case NEWLINE: + { + newline(); + break; + } + case EOF: + { + match(Token.EOF_TYPE); + break; + } + default: + { + throw new NoViableAltException(LT(1), getFilename()); + } + } + } + + public final void openTag() throws RecognitionException, TokenStreamException { + + Token name = null; + + try { // for error handling + match(LT); + name = LT(1); + match(ALPHANUMERICWORD); + + + + sanitizer.validateHtmlElement(name); + + if (isSeamTextElement(name)) { + if (isList(name)) { + validateNestedMarkup(name, htmlElementStack); + } else if (isListItem(name)) { + append(createSeamTextList(name,htmlElementStack)); + } else if (isHeader(name)) { + validateNestedMarkup(name, htmlElementStack); + append(createSeamTextHeader(name)); + } + + } else { + append("<"); + append(name.getText()); + } + htmlElementStack.push(name); + + + } + catch (RecognitionException ex) { + + if (htmlElementStack.isEmpty()) throw ex; + Token tok = htmlElementStack.peek(); + if (tok != null) { + throw new HtmlRecognitionException(tok, ex); + } else { + throw ex; + } + + } + } + + public final void attribute() throws RecognitionException, TokenStreamException { + + Token att = null; + + try { // for error handling + att = LT(1); + match(ALPHANUMERICWORD); + { + _loop422: + do { + if ((LA(1)==SPACE)) { + space(); + } + else { + break _loop422; + } + + } while (true); + } + match(EQ); + { + _loop424: + do { + if ((LA(1)==SPACE)) { + space(); + } + else { + break _loop424; + } + + } while (true); + } + match(DOUBLEQUOTE); + + Token token = htmlElementStack.peek(); + sanitizer.validateHtmlAttribute(token, att); + boolean isSeamTextProcessed = isSeamTextElement(token); + + if (!isSeamTextProcessed) { + append(att.getText()); + append("=\""); + } + beginCapture(); + + attributeValue(); + + String attValue = endCapture(); + sanitizer.validateHtmlAttributeValue(token, att, attValue); + + if (!isSeamTextProcessed) { + append(attValue); + } else if(isLink(token) && "href".equals(att.getText())) { + + linkHolder = attValue; + } + + + match(DOUBLEQUOTE); + + if(!isSeamTextProcessed) { + append("\""); + } + + } + catch (RecognitionException ex) { + + if (htmlElementStack.isEmpty()) throw ex; + Token tok = htmlElementStack.peek(); + if (tok != null) { + throw new HtmlRecognitionException(tok, ex); + } else { + throw ex; + } + + } + } + + public final void beforeBody() throws RecognitionException, TokenStreamException { + + + try { // for error handling + match(GT); + + Token name = htmlElementStack.peek(); + if(isSeamTextElement(name)){ + append(createSimpleSeamText(name)); + } else { + append(">"); + } + + } + catch (RecognitionException ex) { + + if (htmlElementStack.isEmpty()) throw ex; + Token tok = htmlElementStack.peek(); + if (tok != null) { + throw new HtmlRecognitionException(tok, ex); + } else { + throw ex; + } + + } + } + + public final void body() throws RecognitionException, TokenStreamException { + + Token newline = null; + + { + + Token token = htmlElementStack.peek(); + boolean isLink = isLink(token); + linkValueCollector = new StringBuilder(); + + { + _loop415: + do { + switch ( LA(1)) { + case STAR: + case BAR: + case HAT: + case PLUS: + case EQ: + case HASH: + case ESCAPE: + case TWIDDLE: + case OPEN: + case CLOSE: + case BACKTICK: + case GT: + { + seamCharacters(); + break; + } + case ALPHANUMERICWORD: + case UNICODEWORD: + case PUNCTUATION: + case SINGLEQUOTE: + case SLASH: + case SPACE: + { + if(isLink) { + beginCapture(); + } + + + plain(); + + if(isLink) { + String plain = endCapture(); + linkValueCollector.append(plain); + } + + + break; + } + case DOUBLEQUOTE: + case ESCAPED_LT: + case ESCAPED_GT: + case ESCAPED_AMP: + case ESCAPED_QOUT: + { + htmlSpecialChars(); + + if(isLink) { + String message = "unexpected token"; + throw new SemanticException(message); + } + + break; + } + case NEWLINE: + { + newline = LT(1); + match(NEWLINE); + break; + } + default: + if ((LA(1)==LT) && (LA(2)==ALPHANUMERICWORD)) { + html(); + } + else { + break _loop415; + } + } + } while (true); + } + } + } + + public final void closeTagWithBody() throws RecognitionException, TokenStreamException { + + Token name = null; + + match(LT); + match(SLASH); + name = LT(1); + match(ALPHANUMERICWORD); + match(GT); + + if(isSeamTextElement(name)){ + if(isLink(name)){ + append(createSeamTextLink(linkHolder,linkValueCollector.toString().trim())); + } else { + append(createSimpleSeamText(name)); + } + + if(isListItem(name) || isHeader(name)) { + append("\n"); + validateHeaderMarkup(name,htmlElementStack); + } + + } else { + append("</"); + append(name.getText()); + append(">"); + } + + + htmlElementStack.pop(); + + } + + public final void closeTagWithNoBody() throws RecognitionException, TokenStreamException { + + + match(SLASH); + match(GT); + append("/>"); + htmlElementStack.pop(); + + } + + public final void attributeValue() throws RecognitionException, TokenStreamException { + + Token an = null; + Token p = null; + Token s = null; + + try { // for error handling + { + _loop427: + do { + switch ( LA(1)) { + case AMPERSAND: + { + match(AMPERSAND); + append("&amp;"); + break; + } + case ALPHANUMERICWORD: + { + an = LT(1); + match(ALPHANUMERICWORD); + append( an.getText() ); + break; + } + case PUNCTUATION: + { + p = LT(1); + match(PUNCTUATION); + append( p.getText() ); + break; + } + case SLASH: + { + s = LT(1); + match(SLASH); + append( s.getText() ); + break; + } + case SPACE: + { + space(); + break; + } + case STAR: + case BAR: + case HAT: + case PLUS: + case EQ: + case HASH: + case ESCAPE: + case TWIDDLE: + case UNDERSCORE: + { + specialChars(); + break; + } + default: + { + break _loop427; + } + } + } while (true); + } + } + catch (RecognitionException ex) { + + if (htmlElementStack.isEmpty()) throw ex; + Token tok = htmlElementStack.peek(); + if (tok != null) { + throw new HtmlRecognitionException(tok, ex); + } else { + throw ex; + } + + } + } + + + public static final String[] _tokenNames = { + "<0>", + "the end of the text", + "<2>", + "NULL_TREE_LOOKAHEAD", + "letters or digits", + "letters or digits", + "a doublequote \\\"", + "ESCAPED_LT", + "ESCAPED_GT", + "ESCAPED_AMP", + "ESCAPED_QOUT", + "a punctuation character", + "a single quote '", + "a slash '/'", + "a star '*'", + "a bar or pipe '|'", + "a caret '^'", + "a plus '+'", + "an equals '='", + "a hash '#'", + "the escaping blackslash '\\'", + "a tilde '~'", + "an underscore '_'", + "an opening square bracket '['", + "a closing square bracket ']'", + "a backtick '`'", + "a closing angle bracket '>'", + "a space or tab", + "a newline", + "an opening angle bracket '<'", + "an ampersand '&'" + }; + + private static final long[] mk_tokenSet_0() { + long[] data = { 801112048L, 0L}; + return data; + } + public static final BitSet _tokenSet_0 = new BitSet(mk_tokenSet_0()); + + } Added: trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextParserTokenTypes.java =================================================================== --- trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextParserTokenTypes.java (rev 0) +++ trunk/sandbox/ui/editor/src/main/java/org/richfaces/antlr/HtmlSeamTextParserTokenTypes.java 2008-10-30 10:04:25 UTC (rev 10975) @@ -0,0 +1,35 @@ +// $ANTLR : "html-seamtext.g" -> "HtmlSeamTextLexer.java"$ + + package org.richfaces.antlr; + +public interface HtmlSeamTextParserTokenTypes { + int EOF = 1; + int NULL_TREE_LOOKAHEAD = 3; + int ALPHANUMERICWORD = 4; + int UNICODEWORD = 5; + int DOUBLEQUOTE = 6; + int ESCAPED_LT = 7; + int ESCAPED_GT = 8; + int ESCAPED_AMP = 9; + int ESCAPED_QOUT = 10; + int PUNCTUATION = 11; + int SINGLEQUOTE = 12; + int SLASH = 13; + int STAR = 14; + int BAR = 15; + int HAT = 16; + int PLUS = 17; + int EQ = 18; + int HASH = 19; + int ESCAPE = 20; + int TWIDDLE = 21; + int UNDERSCORE = 22; + int OPEN = 23; + int CLOSE = 24; + int BACKTICK = 25; + int GT = 26; + int SPACE = 27; + int NEWLINE = 28; + int LT = 29; + int AMPERSAND = 30; +}