/* The following code was generated by JFlex 1.4.1 on 2/25/10 4:07 PM */ /* * 01/24/2005 * * XMLTokenMaker.java - Generates tokens for XML syntax highlighting. * Copyright (C) 2005 Robert Futrell * robert_futrell at users.sourceforge.net * http://fifesoft.com/rsyntaxtextarea * * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * * This library is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * * You should have received a copy of the GNU Lesser General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. */ package org.fife.ui.rsyntaxtextarea.modes; import java.io.*; import javax.swing.text.Segment; import org.fife.ui.rsyntaxtextarea.*; /** * Scanner for XML. * * This implementation was created using <a href="http://www.jflex.de/">JFlex</a> 1.4.1; however, the generated file was * modified for performance. Memory allocation needs to be almost completely removed to be competitive with the * handwritten lexers (subclasses of <code>AbstractTokenMaker</code>, so this class has been modified so that Strings * are never allocated (via yytext()), and the scanner never has to worry about refilling its buffer (needlessly copying * chars around). We can achieve this because RText always scans exactly 1 line of tokens at a time, and hands the * scanner this line as an array of characters (a Segment really). Since tokens contain pointers to char arrays instead * of Strings holding their contents, there is no need for allocating new memory for Strings. * <p> * * The actual algorithm generated for scanning has, of course, not been modified. * <p> * * If you wish to regenerate this file yourself, keep in mind the following: * <ul> * <li>The generated <code>XMLTokenMaker.java</code> file will contain two definitions of both <code>zzRefill</code> and * <code>yyreset</code>. You should hand-delete the second of each definition (the ones generated by the lexer), as * these generated methods modify the input buffer, which we'll never have to do.</li> * <li>You should also change the declaration/definition of zzBuffer to NOT be initialized. This is a needless memory * allocation for us since we will be pointing the array somewhere else anyway.</li> * <li>You should NOT call <code>yylex()</code> on the generated scanner directly; rather, you should use * <code>getTokenList</code> as you would with any other <code>TokenMaker</code> instance.</li> * </ul> * * @author Robert Futrell * @version 0.5 * */ public class XMLTokenMaker extends AbstractMarkupTokenMaker { /** This character denotes the end of file */ public static final int YYEOF = -1; /** lexical states */ public static final int INTAG = 4; public static final int DTD = 3; public static final int INATTR_DOUBLE = 5; public static final int YYINITIAL = 0; public static final int COMMENT = 1; public static final int CDATA = 7; public static final int INATTR_SINGLE = 6; public static final int PI = 2; /** * Translates characters to character classes */ private static final String ZZ_CMAP_PACKED = "\11\0\1\6\1\4\1\0\1\3\23\0\1\6\1\12\1\26\3\0" + "\1\7\1\11\5\0\1\22\1\2\1\24\12\2\1\1\1\10\1\5" + "\1\25\1\21\1\23\1\0\1\16\1\1\1\14\1\15\17\1\1\17" + "\6\1\1\13\1\0\1\20\1\0\1\1\1\0\32\1\uff85\0"; /** * Translates characters to character classes */ private static final char[] ZZ_CMAP = zzUnpackCMap(ZZ_CMAP_PACKED); /** * Translates DFA states to action switch labels. */ private static final int[] ZZ_ACTION = zzUnpackAction(); private static final String ZZ_ACTION_PACKED_0 = "\5\0\2\1\1\0\2\2\1\3\1\4\1\5\1\6" + "\1\1\1\7\2\1\1\10\2\1\1\11\1\12\2\13" + "\1\14\1\15\1\16\1\17\1\20\1\1\1\21\1\1" + "\1\22\2\1\1\23\1\24\1\25\1\4\1\6\1\0" + "\1\26\3\0\1\27\1\30\1\31\1\0\1\32\4\0" + "\1\33"; private static int[] zzUnpackAction() { int[] result = new int[56]; int offset = 0; offset = zzUnpackAction(ZZ_ACTION_PACKED_0, offset, result); return result; } private static int zzUnpackAction(String packed, int offset, int[] result) { int i = 0; /* index in packed string */ int j = offset; /* index in unpacked array */ int l = packed.length(); while (i < l) { int count = packed.charAt(i++); int value = packed.charAt(i++); do result[j++] = value; while (--count > 0); } return j; } /** * Translates a state to a row index in the transition table */ private static final int[] ZZ_ROWMAP = zzUnpackRowMap(); private static final String ZZ_ROWMAP_PACKED_0 = "\0\0\0\27\0\56\0\105\0\134\0\163\0\212\0\241" + "\0\270\0\317\0\346\0\375\0\u0114\0\u012b\0\u0142\0\346" + "\0\u0159\0\u0170\0\346\0\u0187\0\u019e\0\346\0\346\0\u01b5" + "\0\u01cc\0\346\0\346\0\u01e3\0\346\0\346\0\u01fa\0\346" + "\0\u0211\0\346\0\u0228\0\u023f\0\u0256\0\u026d\0\346\0\u0284" + "\0\346\0\u029b\0\346\0\u02b2\0\u02c9\0\u02e0\0\u02f7\0\346" + "\0\346\0\u030e\0\346\0\u0325\0\u033c\0\u0353\0\u036a\0\346"; private static int[] zzUnpackRowMap() { int[] result = new int[56]; int offset = 0; offset = zzUnpackRowMap(ZZ_ROWMAP_PACKED_0, offset, result); return result; } private static int zzUnpackRowMap(String packed, int offset, int[] result) { int i = 0; /* index in packed string */ int j = offset; /* index in unpacked array */ int l = packed.length(); while (i < l) { int high = packed.charAt(i++) << 16; result[j++] = high | packed.charAt(i++); } return j; } /** * The transition table of the DFA */ private static final int[] ZZ_TRANS = zzUnpackTrans(); private static final String ZZ_TRANS_PACKED_0 = "\3\11\1\12\1\13\1\14\1\15\1\16\17\11\4\17" + "\1\20\15\17\1\21\4\17\4\22\1\23\16\22\1\24" + "\3\22\4\25\1\26\14\25\1\27\5\25\3\30\1\31" + "\1\0\1\30\1\15\2\30\1\32\7\30\1\33\2\30" + "\1\34\1\35\1\36\26\37\1\40\11\41\1\42\15\41" + "\20\43\1\44\6\43\4\11\4\0\22\11\1\12\2\0" + "\1\15\1\0\17\11\30\0\1\45\10\0\1\46\1\0" + "\4\45\3\0\1\47\1\50\5\0\1\15\2\0\1\15" + "\20\0\6\16\1\0\1\16\1\51\16\16\4\17\1\0" + "\15\17\1\0\4\17\22\0\1\52\4\0\4\22\1\0" + "\16\22\1\0\3\22\21\0\1\53\5\0\4\25\1\0" + "\14\25\1\0\5\25\4\30\1\0\1\30\1\0\2\30" + "\1\0\7\30\1\0\2\30\3\0\3\30\1\31\1\0" + "\1\30\1\15\2\30\1\0\7\30\1\0\2\30\24\0" + "\1\33\5\0\26\37\1\0\11\41\1\0\15\41\20\43" + "\1\0\6\43\20\0\1\54\7\0\2\45\11\0\4\45" + "\2\0\1\45\17\0\1\55\6\0\1\56\5\0\1\57" + "\12\0\4\57\30\0\1\60\26\0\1\61\21\0\1\62" + "\34\0\1\63\5\0\2\57\11\0\4\57\2\0\1\57" + "\21\0\1\64\27\0\1\65\27\0\1\66\25\0\1\67" + "\23\0\1\70\13\0"; private static int[] zzUnpackTrans() { int[] result = new int[897]; int offset = 0; offset = zzUnpackTrans(ZZ_TRANS_PACKED_0, offset, result); return result; } private static int zzUnpackTrans(String packed, int offset, int[] result) { int i = 0; /* index in packed string */ int j = offset; /* index in unpacked array */ int l = packed.length(); while (i < l) { int count = packed.charAt(i++); int value = packed.charAt(i++); value--; do result[j++] = value; while (--count > 0); } return j; } /* error codes */ private static final int ZZ_UNKNOWN_ERROR = 0; private static final int ZZ_NO_MATCH = 1; private static final int ZZ_PUSHBACK_2BIG = 2; /* error messages for the codes above */ private static final String ZZ_ERROR_MSG[] = { "Unkown internal scanner error", "Error: could not match input", "Error: pushback value was too large" }; /** * ZZ_ATTRIBUTE[aState] contains the attributes of state <code>aState</code> */ private static final int[] ZZ_ATTRIBUTE = zzUnpackAttribute(); private static final String ZZ_ATTRIBUTE_PACKED_0 = "\5\0\2\1\1\0\2\1\1\11\4\1\1\11\2\1" + "\1\11\2\1\2\11\2\1\2\11\1\1\2\11\1\1" + "\1\11\1\1\1\11\4\1\1\11\1\1\1\11\1\0" + "\1\11\3\0\1\1\2\11\1\0\1\11\4\0\1\11"; private static int[] zzUnpackAttribute() { int[] result = new int[56]; int offset = 0; offset = zzUnpackAttribute(ZZ_ATTRIBUTE_PACKED_0, offset, result); return result; } private static int zzUnpackAttribute(String packed, int offset, int[] result) { int i = 0; /* index in packed string */ int j = offset; /* index in unpacked array */ int l = packed.length(); while (i < l) { int count = packed.charAt(i++); int value = packed.charAt(i++); do result[j++] = value; while (--count > 0); } return j; } /** the input device */ private java.io.Reader zzReader; /** the current state of the DFA */ private int zzState; /** the current lexical state */ private int zzLexicalState = YYINITIAL; /** * this buffer contains the current text to be matched and is the source of the yytext() string */ private char zzBuffer[]; /** the textposition at the last accepting state */ private int zzMarkedPos; /** the current text position in the buffer */ private int zzCurrentPos; /** startRead marks the beginning of the yytext() string in the buffer */ private int zzStartRead; /** * endRead marks the last character in the buffer, that has been read from input */ private int zzEndRead; /** zzAtEOF == true <=> the scanner is at the EOF */ private boolean zzAtEOF; /* user code: */ /** * Token type specific to XMLTokenMaker; this signals that the user has ended a line with an unclosed XML tag; thus * a new line is beginning still inside of the tag. */ public static final int INTERNAL_INTAG = -1; /** * Whether closing markup tags are automatically completed for HTML. */ private static boolean completeCloseTags; /** * Constructor. This must be here because JFlex does not generate a no-parameter constructor. */ public XMLTokenMaker() { } static { completeCloseTags = true; } /** * Adds the token specified to the current linked list of tokens. * * @param tokenType * The token's type. */ private void addToken(int tokenType) { addToken(zzStartRead, zzMarkedPos - 1, tokenType); } /** * Adds the token specified to the current linked list of tokens. * * @param tokenType * The token's type. */ private void addToken(int start, int end, int tokenType) { int so = start + offsetShift; addToken(zzBuffer, start, end, tokenType, so); } /** * Adds the token specified to the current linked list of tokens. * * @param array * The character array. * @param start * The starting offset in the array. * @param end * The ending offset in the array. * @param tokenType * The token's type. * @param startOffset * The offset in the document at which this token occurs. */ public void addToken(char[] array, int start, int end, int tokenType, int startOffset) { super.addToken(array, start, end, tokenType, startOffset); zzStartRead = zzMarkedPos; } /** * Returns whether markup close tags should be completed. For XML, the default value is <code>true</code>. * * @return Whether closing markup tags are completed. * @see #setCompleteCloseTags(boolean) */ public boolean getCompleteCloseTags() { return completeCloseTags; } /** * Static version of {@link #getCompleteCloseTags()}. This hack is unfortunately needed for applications to be able * to query this value without instantiating this class. * * @return Whether closing markup tags are completed. * @see #setCompleteCloseTags(boolean) */ public static boolean getCompleteCloseMarkupTags() { return completeCloseTags; } /** * Always returns <tt>false</tt>, as you never want "mark occurrences" working in XML files. * * @param type * The token type. * @return Whether tokens of this type should have "mark occurrences" enabled. */ public boolean getMarkOccurrencesOfTokenType(int type) { return false; } /** * Returns the first token in the linked list of tokens generated from <code>text</code>. This method must be * implemented by subclasses so they can correctly implement syntax highlighting. * * @param text * The text from which to get tokens. * @param initialTokenType * The token type we should start with. * @param startOffset * The offset into the document at which <code>text</code> starts. * @return The first <code>Token</code> in a linked list representing the syntax highlighted text. */ public Token getTokenList(Segment text, int initialTokenType, int startOffset) { resetTokenList(); this.offsetShift = -text.offset + startOffset; // Start off in the proper state. int state = Token.NULL; switch (initialTokenType) { case Token.COMMENT_MULTILINE: state = COMMENT; start = text.offset; break; case Token.FUNCTION: state = DTD; start = text.offset; break; case Token.LITERAL_STRING_DOUBLE_QUOTE: state = INATTR_DOUBLE; start = text.offset; break; case Token.LITERAL_CHAR: state = INATTR_SINGLE; start = text.offset; break; case Token.PREPROCESSOR: state = PI; start = text.offset; break; case INTERNAL_INTAG: state = INTAG; start = text.offset; break; case Token.VARIABLE: state = CDATA; start = text.offset; break; default: state = Token.NULL; } s = text; try { yyreset(zzReader); yybegin(state); return yylex(); } catch (IOException ioe) { ioe.printStackTrace(); return new DefaultToken(); } } /** * Sets whether markup close tags should be completed. * * @param complete * Whether closing markup tags are completed. * @see #getCompleteCloseTags() */ public static void setCompleteCloseTags(boolean complete) { completeCloseTags = complete; } /** * Refills the input buffer. * * @return <code>true</code> if EOF was reached, otherwise <code>false</code>. */ private boolean zzRefill() { return zzCurrentPos >= s.offset + s.count; } /** * Resets the scanner to read from a new input stream. Does not close the old reader. * * All internal variables are reset, the old input stream <b>cannot</b> be reused (internal buffer is discarded and * lost). Lexical state is set to <tt>YY_INITIAL</tt>. * * @param reader * the new input stream */ public final void yyreset(java.io.Reader reader) { // 's' has been updated. zzBuffer = s.array; /* * We replaced the line below with the two below it because zzRefill no longer "refills" the buffer (since the * way we do it, it's always "full" the first time through, since it points to the segment's array). So, we * assign zzEndRead here. */ // zzStartRead = zzEndRead = s.offset; zzStartRead = s.offset; zzEndRead = zzStartRead + s.count - 1; zzCurrentPos = zzMarkedPos = s.offset; zzLexicalState = YYINITIAL; zzReader = reader; zzAtEOF = false; } /** * Creates a new scanner There is also a java.io.InputStream version of this constructor. * * @param in * the java.io.Reader to read input from. */ public XMLTokenMaker(java.io.Reader in) { this.zzReader = in; } /** * Creates a new scanner. There is also java.io.Reader version of this constructor. * * @param in * the java.io.Inputstream to read input from. */ public XMLTokenMaker(java.io.InputStream in) { this(new java.io.InputStreamReader(in)); } /** * Unpacks the compressed character translation table. * * @param packed * the packed character translation table * @return the unpacked character translation table */ private static char[] zzUnpackCMap(String packed) { char[] map = new char[0x10000]; int i = 0; /* index in packed string */ int j = 0; /* index in unpacked array */ while (i < 78) { int count = packed.charAt(i++); char value = packed.charAt(i++); do map[j++] = value; while (--count > 0); } return map; } /** * Closes the input stream. */ public final void yyclose() throws java.io.IOException { zzAtEOF = true; /* indicate end of file */ zzEndRead = zzStartRead; /* invalidate buffer */ if (zzReader != null) zzReader.close(); } /** * Returns the current lexical state. */ public final int yystate() { return zzLexicalState; } /** * Enters a new lexical state * * @param newState * the new lexical state */ public final void yybegin(int newState) { zzLexicalState = newState; } /** * Returns the text matched by the current regular expression. */ public final String yytext() { return new String(zzBuffer, zzStartRead, zzMarkedPos - zzStartRead); } /** * Returns the character at position <tt>pos</tt> from the matched text. * * It is equivalent to yytext().charAt(pos), but faster * * @param pos * the position of the character to fetch. A value from 0 to yylength()-1. * * @return the character at position pos */ public final char yycharat(int pos) { return zzBuffer[zzStartRead + pos]; } /** * Returns the length of the matched text region. */ public final int yylength() { return zzMarkedPos - zzStartRead; } /** * Reports an error that occured while scanning. * * In a wellformed scanner (no or only correct usage of yypushback(int) and a match-all fallback rule) this method * will only be called with things that "Can't Possibly Happen". If this method is called, something is seriously * wrong (e.g. a JFlex bug producing a faulty scanner etc.). * * Usual syntax/scanner level error handling should be done in error fallback rules. * * @param errorCode * the code of the errormessage to display */ private void zzScanError(int errorCode) { String message; try { message = ZZ_ERROR_MSG[errorCode]; } catch (ArrayIndexOutOfBoundsException e) { message = ZZ_ERROR_MSG[ZZ_UNKNOWN_ERROR]; } throw new Error(message); } /** * Pushes the specified amount of characters back into the input stream. * * They will be read again by then next call of the scanning method * * @param number * the number of characters to be read again. This number must not be greater than yylength()! */ public void yypushback(int number) { if (number > yylength()) zzScanError(ZZ_PUSHBACK_2BIG); zzMarkedPos -= number; } /** * Resumes scanning until the next regular expression is matched, the end of input is encountered or an I/O-Error * occurs. * * @return the next token * @exception java.io.IOException * if any I/O-Error occurs */ public org.fife.ui.rsyntaxtextarea.Token yylex() throws java.io.IOException { int zzInput; int zzAction; // cached fields: int zzCurrentPosL; int zzMarkedPosL; int zzEndReadL = zzEndRead; char[] zzBufferL = zzBuffer; char[] zzCMapL = ZZ_CMAP; int[] zzTransL = ZZ_TRANS; int[] zzRowMapL = ZZ_ROWMAP; int[] zzAttrL = ZZ_ATTRIBUTE; while (true) { zzMarkedPosL = zzMarkedPos; zzAction = -1; zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL; zzState = zzLexicalState; zzForAction: { while (true) { if (zzCurrentPosL < zzEndReadL) zzInput = zzBufferL[zzCurrentPosL++]; else if (zzAtEOF) { zzInput = YYEOF; break zzForAction; } else { // store back cached positions zzCurrentPos = zzCurrentPosL; zzMarkedPos = zzMarkedPosL; boolean eof = zzRefill(); // get translated positions and possibly new buffer zzCurrentPosL = zzCurrentPos; zzMarkedPosL = zzMarkedPos; zzBufferL = zzBuffer; zzEndReadL = zzEndRead; if (eof) { zzInput = YYEOF; break zzForAction; } else { zzInput = zzBufferL[zzCurrentPosL++]; } } int zzNext = zzTransL[zzRowMapL[zzState] + zzCMapL[zzInput]]; if (zzNext == -1) break zzForAction; zzState = zzNext; int zzAttributes = zzAttrL[zzState]; if ((zzAttributes & 1) == 1) { zzAction = zzState; zzMarkedPosL = zzCurrentPosL; if ((zzAttributes & 8) == 8) break zzForAction; } } } // store back cached position zzMarkedPos = zzMarkedPosL; switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) { case 3: { addNullToken(); return firstToken; } case 28: break; case 4: { addToken(Token.MARKUP_TAG_DELIMITER); yybegin(INTAG); } case 29: break; case 23: { int count = yylength(); addToken(zzStartRead, zzStartRead + 1, Token.MARKUP_TAG_DELIMITER); addToken(zzMarkedPos - (count - 2), zzMarkedPos - 1, Token.MARKUP_TAG_NAME); yybegin(INTAG); } case 30: break; case 17: { yybegin(INTAG); addToken(start, zzStartRead, Token.LITERAL_STRING_DOUBLE_QUOTE); } case 31: break; case 10: { yybegin(YYINITIAL); addToken(start, zzStartRead, Token.FUNCTION); } case 32: break; case 24: { yybegin(YYINITIAL); addToken(start, zzStartRead + 2, Token.COMMENT_MULTILINE); } case 33: break; case 14: { addToken(Token.MARKUP_TAG_DELIMITER); /* Not valid but we'll still accept it */ } case 34: break; case 5: { addToken(Token.WHITESPACE); } case 35: break; case 9: { addToken(start, zzStartRead - 1, Token.FUNCTION); return firstToken; } case 36: break; case 20: { start = zzMarkedPos - 2; yybegin(DTD); } case 37: break; case 2: { addToken(Token.IDENTIFIER); } case 38: break; case 27: { addToken(Token.DATA_TYPE); start = zzMarkedPos; yybegin(CDATA); } case 39: break; case 6: { addToken(Token.DATA_TYPE); } case 40: break; case 19: { int count = yylength(); addToken(zzStartRead, zzStartRead, Token.MARKUP_TAG_DELIMITER); addToken(zzMarkedPos - (count - 1), zzMarkedPos - 1, Token.MARKUP_TAG_NAME); yybegin(INTAG); } case 41: break; case 26: { start = zzMarkedPos - 4; yybegin(COMMENT); } case 42: break; case 25: { int temp = zzStartRead; yybegin(YYINITIAL); addToken(start, zzStartRead - 1, Token.VARIABLE); addToken(temp, zzMarkedPos - 1, Token.DATA_TYPE); } case 43: break; case 21: { start = zzMarkedPos - 2; yybegin(PI); } case 44: break; case 16: { start = zzMarkedPos - 1; yybegin(INATTR_DOUBLE); } case 45: break; case 13: { yybegin(YYINITIAL); addToken(Token.MARKUP_TAG_DELIMITER); } case 46: break; case 12: { start = zzMarkedPos - 1; yybegin(INATTR_SINGLE); } case 47: break; case 8: { addToken(start, zzStartRead - 1, Token.PREPROCESSOR); return firstToken; } case 48: break; case 18: { yybegin(INTAG); addToken(start, zzStartRead, Token.LITERAL_CHAR); } case 49: break; case 22: { yybegin(YYINITIAL); addToken(start, zzStartRead + 1, Token.PREPROCESSOR); } case 50: break; case 15: { addToken(Token.OPERATOR); } case 51: break; case 11: { addToken(Token.MARKUP_TAG_ATTRIBUTE); } case 52: break; case 1: { } case 53: break; case 7: { addToken(start, zzStartRead - 1, Token.COMMENT_MULTILINE); return firstToken; } case 54: break; default: if (zzInput == YYEOF && zzStartRead == zzCurrentPos) { zzAtEOF = true; switch (zzLexicalState) { case INTAG: { addToken(start, zzStartRead - 1, INTERNAL_INTAG); return firstToken; } case 57: break; case DTD: { addToken(start, zzStartRead - 1, Token.FUNCTION); return firstToken; } case 58: break; case INATTR_DOUBLE: { addToken(start, zzStartRead - 1, Token.LITERAL_STRING_DOUBLE_QUOTE); return firstToken; } case 59: break; case YYINITIAL: { addNullToken(); return firstToken; } case 60: break; case COMMENT: { addToken(start, zzStartRead - 1, Token.COMMENT_MULTILINE); return firstToken; } case 61: break; case CDATA: { addToken(start, zzStartRead - 1, Token.VARIABLE); return firstToken; } case 62: break; case INATTR_SINGLE: { addToken(start, zzStartRead - 1, Token.LITERAL_CHAR); return firstToken; } case 63: break; case PI: { addToken(start, zzStartRead - 1, Token.PREPROCESSOR); return firstToken; } case 64: break; default: return null; } } else { zzScanError(ZZ_NO_MATCH); } } } } }