/* The following code was generated by JFlex 1.2.2 on 8/6/16 1:32 PM */
/*******************************************************************************
* Copyright (c) 2004, 2016 IBM Corporation and others.
* All rights reserved. This program and the accompanying materials
* are made available under the terms of the Eclipse Public License v1.0
* which accompanies this distribution, and is available at
* http://www.eclipse.org/legal/epl-v10.html
*
* Contributors:
* IBM Corporation - initial API and implementation
*******************************************************************************/
package org.eclipse.wst.html.core.internal.parser;
import java.io.CharArrayReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import org.eclipse.wst.html.core.internal.contenttype.IntStack;
import org.eclipse.wst.sse.core.internal.ltk.parser.BlockMarker;
import org.eclipse.wst.sse.core.internal.ltk.parser.BlockTokenizer;
import org.eclipse.wst.sse.core.internal.provisional.text.ITextRegion;
import org.eclipse.wst.sse.core.internal.util.Debug;
import org.eclipse.wst.sse.core.utils.StringUtils;
import org.eclipse.wst.xml.core.internal.Logger;
import org.eclipse.wst.xml.core.internal.parser.regions.XMLParserRegionFactory;
import org.eclipse.wst.xml.core.internal.regions.DOMRegionContext;
/**
* Generate with -skel skeleton.sse
*/
/**
* This class is a scanner generated by
* <a href="http://www.informatik.tu-muenchen.de/~kleing/jflex/">JFlex</a> 1.2.2
* on 8/6/16 1:32 PM from the specification file
* <tt>file:/Users/nitin/git/webtools.sourceediting/bundles/org.eclipse.wst.sse.core/DevTimeSupport/SedModel/HTMLTokenizer/devel/HTMLTokenizer.jflex</tt>
*/
public class HTMLTokenizer implements BlockTokenizer, DOMRegionContext {
/** this character denotes the end of file */
final public static int YYEOF = -1;
/** lexical states */
final public static int ST_XML_DOCTYPE_EXTERNAL_ID = 19;
final public static int ST_XML_ELEMENT_DECLARATION_CONTENT = 23;
final public static int ST_XML_PI_TAG_CLOSE = 11;
final public static int ST_XML_DECLARATION_CLOSE = 17;
final public static int ST_XML_PI_ATTRIBUTE_VALUE = 10;
final public static int ST_XML_TAG_NAME = 12;
final public static int ST_XML_ATTRIBUTE_VALUE = 15;
final public static int ST_XML_DOCTYPE_ID_SYSTEM = 21;
final public static int ST_XML_ATTRIBUTE_NAME = 13;
final public static int ST_XML_ELEMENT_DECLARATION = 22;
final public static int ST_XML_DOCTYPE_DECLARATION = 18;
final public static int ST_XML_ATTLIST_DECLARATION = 24;
final public static int ST_XML_COMMENT_END = 4;
final public static int ST_CDATA_TEXT = 1;
final public static int ST_XML_COMMENT = 3;
final public static int ST_PI_CONTENT = 7;
final public static int ST_PI_WS = 6;
final public static int ST_CDATA_END = 2;
final public static int ST_XML_ATTLIST_DECLARATION_CONTENT = 25;
final public static int ST_BLOCK_TAG_SCAN = 26;
final public static int ST_XML_PI_EQUALS = 9;
final public static int ST_XML_DECLARATION = 16;
final public static int YYINITIAL = 0;
final public static int ST_XML_DOCTYPE_ID_PUBLIC = 20;
final public static int ST_XML_EQUALS = 14;
final public static int ST_PI = 5;
final public static int ST_XML_PI_ATTRIBUTE_NAME = 8;
/**
* Translates characters to character classes
*/
final private static String yycmap_packed =
"\11\0\1\5\1\25\2\0\1\20\22\0\1\20\1\24\1\15\1\14"+
"\1\22\1\23\1\16\1\17\1\13\1\13\1\10\1\22\1\22\1\7"+
"\1\6\1\3\12\21\1\10\1\61\1\1\1\46\1\2\1\4\1\22"+
"\1\36\1\62\1\34\1\35\1\51\1\57\1\40\1\40\1\43\1\40"+
"\1\40\1\32\1\30\1\45\1\44\1\50\1\40\1\40\1\56\1\37"+
"\1\60\2\40\1\26\1\47\1\40\1\11\1\0\1\12\1\0\1\10"+
"\1\0\1\53\1\62\1\63\1\54\1\41\1\57\1\40\1\66\1\43"+
"\2\40\1\33\1\31\1\45\1\44\1\50\1\40\1\40\1\42\1\52"+
"\1\60\1\40\1\40\1\27\1\55\1\40\1\0\1\0\72\0\1\65"+
"\10\0\27\64\1\0\37\64\1\0\72\64\2\0\13\64\2\0\10\64"+
"\1\0\65\64\1\0\104\64\11\0\44\64\3\0\2\64\4\0\36\64"+
"\70\0\131\64\22\0\7\64\16\0\2\65\56\0\106\65\32\0\2\65"+
"\44\0\1\64\1\65\3\64\1\0\1\64\1\0\24\64\1\0\54\64"+
"\1\0\7\64\3\0\1\64\1\0\1\64\1\0\1\64\1\0\1\64"+
"\1\0\22\64\15\0\14\64\1\0\102\64\1\0\14\64\1\0\44\64"+
"\1\0\4\65\11\0\65\64\2\0\2\64\2\0\2\64\3\0\34\64"+
"\2\0\10\64\2\0\2\64\67\0\46\64\2\0\1\64\7\0\46\64"+
"\12\0\21\65\1\0\27\65\1\0\3\65\1\0\1\65\1\0\2\65"+
"\1\0\1\65\13\0\33\64\5\0\3\64\56\0\32\64\5\0\1\65"+
"\12\64\10\65\15\0\12\65\6\0\1\65\107\64\2\0\5\64\1\0"+
"\17\64\1\0\4\64\1\0\1\64\17\65\2\64\2\65\1\0\4\65"+
"\2\0\12\65\u0207\0\3\65\1\0\65\64\2\0\1\65\1\64\20\65"+
"\3\0\4\65\3\0\12\64\2\65\2\0\12\65\21\0\3\65\1\0"+
"\10\64\2\0\2\64\2\0\26\64\1\0\7\64\1\0\1\64\3\0"+
"\4\64\2\0\1\65\1\0\7\65\2\0\2\65\2\0\3\65\11\0"+
"\1\65\4\0\2\64\1\0\3\64\2\65\2\0\12\65\2\64\20\0"+
"\1\65\2\0\6\64\4\0\2\64\2\0\26\64\1\0\7\64\1\0"+
"\2\64\1\0\2\64\1\0\2\64\2\0\1\65\1\0\5\65\4\0"+
"\2\65\2\0\3\65\13\0\4\64\1\0\1\64\7\0\12\65\2\65"+
"\3\64\14\0\3\65\1\0\7\64\1\0\1\64\1\0\3\64\1\0"+
"\26\64\1\0\7\64\1\0\2\64\1\0\5\64\2\0\1\65\1\64"+
"\10\65\1\0\3\65\1\0\3\65\22\0\1\64\5\0\12\65\21\0"+
"\3\65\1\0\10\64\2\0\2\64\2\0\26\64\1\0\7\64\1\0"+
"\2\64\2\0\4\64\2\0\1\65\1\64\6\65\3\0\2\65\2\0"+
"\3\65\10\0\2\65\4\0\2\64\1\0\3\64\4\0\12\65\22\0"+
"\2\65\1\0\6\64\3\0\3\64\1\0\4\64\3\0\2\64\1\0"+
"\1\64\1\0\2\64\3\0\2\64\3\0\3\64\3\0\10\64\1\0"+
"\3\64\4\0\5\65\3\0\3\65\1\0\4\65\11\0\1\65\17\0"+
"\11\65\21\0\3\65\1\0\10\64\1\0\3\64\1\0\27\64\1\0"+
"\12\64\1\0\5\64\4\0\7\65\1\0\3\65\1\0\4\65\7\0"+
"\2\65\11\0\2\64\4\0\12\65\22\0\2\65\1\0\10\64\1\0"+
"\3\64\1\0\27\64\1\0\12\64\1\0\5\64\4\0\7\65\1\0"+
"\3\65\1\0\4\65\7\0\2\65\7\0\1\64\1\0\2\64\4\0"+
"\12\65\22\0\2\65\1\0\10\64\1\0\3\64\1\0\27\64\1\0"+
"\20\64\4\0\6\65\2\0\3\65\1\0\4\65\11\0\1\65\10\0"+
"\2\64\4\0\12\65\221\0\56\64\1\0\1\64\1\65\2\64\7\65"+
"\5\0\6\64\1\65\10\65\1\0\12\65\47\0\2\64\1\0\1\64"+
"\2\0\2\64\1\0\1\64\2\0\1\64\6\0\4\64\1\0\7\64"+
"\1\0\3\64\1\0\1\64\1\0\1\64\2\0\2\64\1\0\2\64"+
"\1\0\1\64\1\65\2\64\6\65\1\0\2\65\1\64\2\0\5\64"+
"\1\0\1\65\1\0\6\65\2\0\12\65\76\0\2\65\6\0\12\65"+
"\13\0\1\65\1\0\1\65\1\0\1\65\4\0\2\65\10\64\1\0"+
"\41\64\7\0\24\65\1\0\6\65\4\0\6\65\1\0\1\65\1\0"+
"\25\65\3\0\7\65\1\0\1\65\346\0\46\64\12\0\47\64\11\0"+
"\1\64\1\0\2\64\1\0\3\64\1\0\1\64\1\0\2\64\1\0"+
"\5\64\51\0\1\64\1\0\1\64\1\0\1\64\13\0\1\64\1\0"+
"\1\64\1\0\1\64\3\0\2\64\3\0\1\64\5\0\3\64\1\0"+
"\1\64\1\0\1\64\1\0\1\64\1\0\1\64\3\0\2\64\3\0"+
"\2\64\1\0\1\64\50\0\1\64\11\0\1\64\2\0\1\64\2\0"+
"\2\64\7\0\2\64\1\0\1\64\1\0\7\64\50\0\1\64\4\0"+
"\1\64\10\0\1\64\u0c06\0\234\64\4\0\132\64\6\0\26\64\2\0"+
"\6\64\2\0\46\64\2\0\6\64\2\0\10\64\1\0\1\64\1\0"+
"\1\64\1\0\1\64\1\0\37\64\2\0\65\64\1\0\7\64\1\0"+
"\1\64\3\0\3\64\1\0\7\64\3\0\4\64\2\0\6\64\4\0"+
"\15\64\5\0\3\64\1\0\7\64\323\0\15\65\4\0\1\65\104\0"+
"\1\64\3\0\2\64\2\0\1\64\121\0\3\64\u0e82\0\1\65\1\0"+
"\1\64\31\0\11\64\6\65\1\0\5\65\13\0\124\64\4\0\2\65"+
"\2\0\2\65\2\0\132\64\1\0\3\65\6\0\50\64\u1cd3\0\u51a6\64"+
"\u0c5a\0\u2ba4\64\134\0\u0800\0\u1ffe\0\2\0";
/**
* Translates characters to character classes
*/
final private static char [] yycmap = yy_unpack_cmap(yycmap_packed);
/**
* Translates a state to a row index in the transition table
*/
final private static int yy_rowMap [] = {
0, 55, 110, 165, 220, 275, 330, 385, 440, 495,
550, 605, 660, 715, 770, 825, 880, 935, 990, 1045,
1100, 1155, 1210, 1265, 1320, 1375, 1430, 1485, 1540, 1595,
1650, 1705, 1760, 1705, 1760, 1815, 1705, 1705, 1760, 1870,
1925, 1980, 2035, 2090, 2145, 2200, 1705, 1760, 2255, 2310,
2365, 1705, 2420, 2420, 2475, 2530, 2585, 2255, 2640, 2695,
1705, 2750, 2805, 2860, 2915, 1705, 2970, 3025, 3080, 3135,
3190, 1705, 3245, 3300, 3355, 3410, 3465, 3520, 3575, 3630,
3630, 3685, 3740, 3795, 3850, 3850, 3905, 3960, 4015, 4070,
4070, 4125, 4180, 4235, 4290, 1705, 4345, 4345, 4400, 4455,
4510, 4565, 1705, 1705, 1760, 1705, 1705, 4620, 4675, 4730,
4785, 4840, 4895, 4950, 5005, 5060, 1705, 5115, 5170, 1705,
1705, 2420, 5225, 2530, 1705, 5280, 2585, 1705, 2970, 5335,
3080, 1705, 5390, 3135, 4620, 5445, 5500, 5555, 3410, 1705,
5610, 5665, 3630, 3685, 3630, 5720, 3740, 1705, 5775, 5830,
5885, 5885, 5940, 5995, 3850, 3905, 3850, 6050, 3960, 1705,
6105, 4015, 4070, 6160, 4125, 1705, 6215, 6270, 6325, 6325,
6380, 6435, 6490, 4345, 6545, 4400, 1705, 6600, 6655, 6710,
6710, 6765, 6820, 6875, 6930, 6985, 7040, 7095, 1705, 7150,
7205, 1705, 1705, 1705, 2035, 7260, 7315, 7370, 7425, 7480,
7535, 5775, 7590, 7590, 6215, 7645, 7645, 7700, 6600, 7755,
7755, 7810, 1705, 7865, 7920, 7975, 1705, 8030, 8085, 8140,
8195, 8250, 8305, 8360, 5940, 6380, 8415, 6765, 8470, 8525,
8580, 1705, 8635, 8690, 8745, 8800, 8855, 8910, 8965, 9020,
9075, 9130, 9185, 9240, 9295, 1705, 1705, 9350, 9405, 9460,
9515, 1705, 1705, 1705, 9570, 9625, 9680, 9735, 9790, 9845,
1705, 9900, 4235, 4510, 9955, 10010, 10065, 10120, 2035
};
/**
* The packed transition table of the DFA
*/
final private static String yy_packed =
"\1\34\1\35\14\34\1\36\4\34\1\37\43\34\1\40"+
"\1\41\65\40\1\42\1\43\10\42\1\44\12\42\1\45"+
"\41\42\1\46\1\47\65\46\1\42\1\43\5\42\1\50"+
"\15\42\1\45\42\42\1\43\2\42\1\51\1\52\2\42"+
"\1\53\3\42\1\53\3\42\1\52\4\42\1\52\1\54"+
"\1\55\16\53\1\42\12\53\1\42\3\53\1\42\1\53"+
"\1\42\1\43\2\42\1\51\1\56\12\42\1\56\4\42"+
"\1\56\41\42\1\57\1\60\2\57\1\61\20\57\1\45"+
"\41\57\1\42\1\43\2\42\1\62\1\52\2\42\1\63"+
"\3\42\1\63\3\42\1\52\4\42\1\52\20\63\1\42"+
"\12\63\1\42\3\63\1\42\1\63\1\42\1\43\2\42"+
"\1\62\1\52\2\42\1\63\3\42\1\63\3\42\1\52"+
"\4\42\1\52\20\63\1\64\12\63\1\42\3\63\1\42"+
"\1\63\1\65\1\43\1\42\1\66\1\67\1\52\7\65"+
"\1\70\1\65\1\71\1\52\4\65\1\52\41\65\1\42"+
"\1\43\2\42\1\72\20\42\1\45\41\42\1\73\1\74"+
"\1\75\1\76\4\73\1\77\3\73\1\77\11\73\20\100"+
"\1\73\12\100\1\73\3\100\1\73\1\100\1\42\1\74"+
"\1\75\1\76\1\42\1\52\2\42\5\101\3\42\1\52"+
"\4\42\1\52\20\101\1\42\12\101\1\42\3\101\1\42"+
"\1\101\1\42\1\74\1\75\1\76\1\42\1\52\2\42"+
"\5\101\3\42\1\52\4\42\1\52\20\101\1\102\12\101"+
"\1\42\3\101\1\42\1\101\1\103\1\74\1\75\1\104"+
"\1\103\1\52\7\103\1\105\1\103\1\106\1\52\4\103"+
"\1\52\41\103\1\42\1\107\1\110\2\42\1\52\12\42"+
"\1\52\4\42\1\52\7\42\1\111\1\112\2\42\1\113"+
"\7\42\1\113\1\42\1\112\1\111\13\42\1\43\1\110"+
"\2\42\1\52\3\42\1\114\6\42\1\52\4\42\1\52"+
"\42\42\1\43\1\110\2\42\1\52\2\42\1\115\1\114"+
"\2\42\1\115\3\42\1\52\4\42\1\52\20\115\1\42"+
"\12\115\1\42\3\115\1\42\1\115\1\42\1\43\1\110"+
"\2\42\1\52\3\42\1\114\6\42\1\52\4\42\1\52"+
"\14\42\1\116\5\42\1\117\5\42\1\116\10\42\1\120"+
"\1\43\1\110\1\121\1\120\1\52\3\120\1\122\3\120"+
"\1\123\1\120\1\124\1\52\4\120\1\52\41\120\1\125"+
"\1\43\1\110\1\126\1\125\1\52\3\125\1\127\3\125"+
"\1\130\1\125\1\131\1\52\4\125\1\52\41\125\1\132"+
"\1\43\1\110\1\133\1\132\1\52\7\132\1\134\1\132"+
"\1\135\1\52\4\132\1\52\41\132\1\136\1\137\1\140"+
"\64\136\1\141\1\43\1\110\1\142\1\141\1\52\7\141"+
"\1\143\1\141\1\144\1\52\4\141\1\52\41\141\1\145"+
"\1\146\1\147\64\145\1\150\1\151\65\150\1\34\1\0"+
"\14\34\1\0\4\34\1\0\43\34\3\0\1\152\1\153"+
"\17\0\1\154\47\0\1\155\2\0\1\156\3\0\1\157"+
"\3\0\1\155\4\0\1\155\20\156\1\0\12\156\1\0"+
"\3\156\1\0\1\156\5\0\1\155\2\0\1\160\3\0"+
"\1\160\3\0\1\155\2\0\1\161\1\0\1\155\20\160"+
"\1\0\12\160\1\0\3\160\1\0\1\160\113\0\1\162"+
"\54\0\1\163\63\0\1\164\61\0\1\165\71\0\1\52"+
"\12\0\1\52\4\0\1\52\47\0\7\53\4\0\1\53"+
"\4\0\20\53\1\0\12\53\1\0\5\53\6\0\7\53"+
"\4\0\1\53\4\0\2\53\2\166\14\53\1\0\12\53"+
"\1\0\5\53\6\0\7\53\4\0\1\53\4\0\2\53"+
"\1\166\1\167\14\53\1\0\12\53\1\0\5\53\5\0"+
"\1\56\12\0\1\56\4\0\1\56\43\0\1\170\66\0"+
"\1\171\72\0\7\63\4\0\1\63\4\0\20\63\1\0"+
"\12\63\1\0\5\63\1\65\2\0\1\172\1\65\1\0"+
"\7\65\1\0\1\65\2\0\4\65\1\0\42\65\1\0"+
"\1\171\1\172\1\65\1\0\7\65\1\0\1\65\2\0"+
"\4\65\1\0\41\65\1\70\2\173\1\174\1\70\1\173"+
"\7\70\1\175\1\70\2\173\4\70\1\173\41\70\1\71"+
"\2\176\1\177\1\71\1\176\7\71\1\176\1\71\1\175"+
"\1\176\4\71\1\176\41\71\1\73\3\0\22\73\20\0"+
"\1\73\12\0\1\73\3\0\1\73\4\0\1\152\20\0"+
"\1\154\44\0\1\200\64\0\1\73\3\0\2\73\7\77"+
"\4\73\1\77\4\73\20\100\1\73\12\100\1\73\3\100"+
"\1\77\1\100\6\0\7\100\4\0\1\100\4\0\20\100"+
"\1\0\12\100\1\0\5\100\6\0\7\101\4\0\1\101"+
"\4\0\20\101\1\0\12\101\1\0\5\101\1\103\2\0"+
"\1\201\1\103\1\0\7\103\1\0\1\103\2\0\4\103"+
"\1\0\42\103\1\0\1\200\1\201\1\103\1\0\7\103"+
"\1\0\1\103\2\0\4\103\1\0\41\103\1\105\2\202"+
"\1\203\1\105\1\202\7\105\1\204\1\105\2\202\4\105"+
"\1\202\41\105\1\106\2\205\1\206\1\106\1\205\7\106"+
"\1\205\1\106\1\204\1\205\4\106\1\205\41\106\3\0"+
"\1\152\20\0\1\207\106\0\1\210\61\0\1\211\12\0"+
"\1\211\46\0\2\212\33\0\12\213\1\214\54\213\6\0"+
"\7\115\4\0\1\115\4\0\20\115\1\0\12\115\1\0"+
"\5\115\47\0\1\215\5\0\1\215\71\0\1\216\6\0"+
"\1\120\2\0\1\217\1\120\1\0\7\120\1\0\1\120"+
"\2\0\4\120\1\0\41\120\1\122\2\213\1\220\1\122"+
"\1\213\4\122\1\221\2\122\1\213\1\122\2\213\4\122"+
"\1\213\41\122\1\123\2\222\1\223\1\123\1\222\7\123"+
"\1\224\1\123\2\222\4\123\1\222\41\123\1\225\2\226"+
"\1\227\1\230\1\226\3\230\2\225\2\230\1\226\1\225"+
"\1\231\1\232\4\230\1\232\36\230\2\225\1\230\1\125"+
"\2\0\1\233\1\125\1\0\7\125\1\0\1\125\2\0"+
"\4\125\1\0\41\125\1\127\2\213\1\234\1\127\1\213"+
"\4\127\1\235\2\127\1\213\1\127\2\213\4\127\1\213"+
"\41\127\1\130\2\236\1\237\1\130\1\236\7\130\1\240"+
"\1\130\2\236\4\130\1\236\41\130\1\131\2\241\1\242"+
"\1\131\1\241\7\131\1\241\1\131\1\240\1\241\4\131"+
"\1\241\41\131\1\132\2\0\1\243\1\132\1\0\7\132"+
"\1\0\1\132\2\0\4\132\1\0\41\132\1\134\2\244"+
"\1\245\1\134\1\244\7\134\1\246\1\134\2\244\4\134"+
"\1\244\41\134\1\247\2\250\1\251\1\252\1\250\3\252"+
"\2\247\2\252\1\250\1\247\1\253\1\254\4\252\1\254"+
"\36\252\2\247\1\252\2\136\1\0\66\136\1\0\21\136"+
"\1\255\42\136\1\141\2\0\1\256\1\141\1\0\7\141"+
"\1\0\1\141\2\0\4\141\1\0\41\141\1\143\2\257"+
"\1\260\1\143\1\257\7\143\1\261\1\143\2\257\4\143"+
"\1\257\41\143\1\262\2\263\1\264\1\265\1\263\3\265"+
"\2\262\2\265\1\263\1\262\1\266\1\267\4\265\1\267"+
"\36\265\2\262\1\265\2\145\1\0\66\145\1\0\21\145"+
"\1\270\42\145\7\0\1\271\1\0\1\272\62\0\1\155"+
"\2\0\1\34\3\0\1\34\3\0\1\155\4\0\1\155"+
"\20\34\1\0\12\34\1\0\3\34\1\0\1\34\1\273"+
"\1\0\3\273\1\274\7\156\1\273\1\0\1\273\1\274"+
"\1\156\1\273\1\0\1\273\1\274\20\156\1\273\12\156"+
"\1\275\5\156\1\273\1\0\3\273\1\274\7\156\1\273"+
"\1\0\1\273\1\274\1\276\1\273\1\0\1\273\1\274"+
"\1\156\1\277\16\156\1\273\12\156\1\275\5\156\1\273"+
"\1\0\3\273\1\274\7\160\1\273\1\0\1\273\1\274"+
"\1\160\1\273\1\0\1\273\1\274\20\160\1\273\12\160"+
"\1\300\5\160\23\0\1\161\54\0\1\272\57\0\1\301"+
"\66\0\1\302\72\0\7\53\4\0\1\53\4\0\4\53"+
"\2\303\12\53\1\0\12\53\1\0\5\53\6\0\7\53"+
"\4\0\1\53\4\0\4\53\1\303\1\304\12\53\1\0"+
"\12\53\1\0\5\53\15\173\1\175\51\173\17\176\1\175"+
"\47\176\15\202\1\204\51\202\17\205\1\204\47\205\34\0"+
"\1\305\26\0\1\305\42\0\1\306\12\0\1\306\55\0"+
"\1\307\7\0\1\307\57\0\1\310\13\0\1\310\72\0"+
"\1\311\4\0\15\222\1\224\51\222\1\225\2\226\1\312"+
"\1\225\1\226\7\225\1\226\1\225\1\224\1\226\4\225"+
"\1\226\41\225\17\226\1\224\47\226\1\225\2\226\1\312"+
"\1\225\1\226\7\225\1\226\1\225\1\313\1\226\4\225"+
"\1\226\41\225\17\0\1\314\47\0\17\226\1\313\47\226"+
"\15\236\1\240\51\236\17\241\1\240\47\241\15\244\1\246"+
"\51\244\1\247\2\250\1\315\1\247\1\250\7\247\1\250"+
"\1\247\1\246\1\250\4\247\1\250\41\247\17\250\1\246"+
"\47\250\1\247\2\250\1\315\1\247\1\250\7\247\1\250"+
"\1\247\1\316\1\250\4\247\1\250\41\247\17\0\1\317"+
"\47\0\17\250\1\316\47\250\2\136\1\0\6\136\1\320"+
"\55\136\15\257\1\261\51\257\1\262\2\263\1\321\1\262"+
"\1\263\7\262\1\263\1\262\1\261\1\263\4\262\1\263"+
"\41\262\17\263\1\261\47\263\1\262\2\263\1\321\1\262"+
"\1\263\7\262\1\263\1\262\1\322\1\263\4\262\1\263"+
"\41\262\17\0\1\323\47\0\17\263\1\322\47\263\2\145"+
"\1\0\6\145\1\324\55\145\7\0\1\325\113\0\1\326"+
"\32\0\1\273\1\0\14\273\1\0\4\273\1\0\35\273"+
"\1\0\6\273\1\0\3\273\1\274\2\273\1\327\3\273"+
"\1\327\1\273\1\0\1\273\1\274\2\273\1\0\1\273"+
"\1\274\20\327\1\273\12\327\1\330\3\327\1\273\1\327"+
"\1\273\1\0\3\273\1\274\7\156\1\273\1\0\1\273"+
"\1\274\1\276\1\273\1\0\1\273\1\274\20\156\1\273"+
"\12\156\1\331\5\156\1\273\1\0\3\273\1\274\7\156"+
"\1\273\1\0\1\273\1\274\1\332\1\273\1\0\1\273"+
"\1\274\6\156\3\332\2\156\1\332\4\156\1\273\2\156"+
"\1\332\1\156\2\332\2\156\1\332\1\156\1\275\2\332"+
"\3\156\6\0\1\53\1\333\5\53\4\0\1\53\4\0"+
"\20\53\1\0\12\53\1\0\5\53\37\0\1\334\12\0"+
"\1\334\46\0\2\335\63\0\2\336\74\0\1\337\12\0"+
"\1\337\46\0\2\340\36\0\2\341\1\0\3\341\2\0"+
"\2\341\2\0\1\231\44\341\2\0\1\341\3\0\2\342"+
"\1\0\3\342\2\0\2\342\2\0\1\253\44\342\2\0"+
"\1\342\2\136\1\0\31\136\1\343\32\136\3\0\2\344"+
"\1\0\3\344\2\0\2\344\2\0\1\266\44\344\2\0"+
"\1\344\2\145\1\0\31\145\1\345\32\145\35\0\1\346"+
"\31\0\1\273\1\0\3\273\1\347\7\327\1\273\1\0"+
"\1\273\1\347\1\327\1\273\1\0\1\273\1\347\20\327"+
"\1\273\12\327\1\350\5\327\61\0\1\330\5\0\1\273"+
"\1\0\3\273\1\274\7\156\1\273\1\0\1\273\1\274"+
"\1\332\1\273\1\0\1\273\1\274\6\156\3\332\2\156"+
"\1\332\4\156\1\273\2\156\1\332\1\156\2\332\2\156"+
"\1\332\1\156\1\331\2\332\3\156\6\0\7\53\4\0"+
"\1\53\4\0\14\53\1\351\3\53\1\0\12\53\1\0"+
"\5\53\47\0\1\352\5\0\1\352\54\0\1\353\64\0"+
"\1\354\7\0\1\354\56\0\1\355\7\0\1\355\60\0"+
"\1\356\23\0\2\136\1\0\32\136\1\357\31\136\2\145"+
"\1\0\32\145\1\360\31\145\36\0\1\361\30\0\1\273"+
"\1\0\3\273\1\347\2\273\1\327\3\273\1\327\1\273"+
"\1\0\1\273\1\347\2\273\1\0\1\273\1\347\20\327"+
"\1\273\12\327\1\0\3\327\1\273\1\327\6\0\7\53"+
"\4\0\1\53\4\0\20\53\1\0\3\53\1\362\6\53"+
"\1\0\5\53\50\0\1\363\60\0\1\364\13\0\1\364"+
"\55\0\1\365\51\0\2\366\71\0\1\367\26\0\1\367"+
"\3\0\2\136\1\0\33\136\1\370\30\136\2\145\1\0"+
"\33\145\1\371\30\145\37\0\1\372\35\0\7\53\4\0"+
"\1\53\4\0\20\53\1\0\6\53\1\373\3\53\1\0"+
"\5\53\41\0\1\374\7\0\1\374\54\0\1\375\12\0"+
"\1\375\53\0\1\376\12\0\1\376\14\0\2\136\1\0"+
"\34\136\1\377\27\136\2\145\1\0\34\145\1\u0100\27\145"+
"\36\0\1\u0101\36\0\7\53\4\0\1\53\4\0\5\53"+
"\1\u0102\12\53\1\0\12\53\1\0\5\53\2\136\1\0"+
"\33\136\1\u0103\30\136\2\145\1\0\33\145\1\u0104\30\145"+
"\11\0\1\u0105\63\0\7\53\4\0\1\53\4\0\13\53"+
"\1\u0106\4\53\1\0\12\53\1\0\5\53\2\136\1\0"+
"\6\136\1\u0107\55\136\2\145\1\0\6\145\1\u0108\55\145"+
"\6\0\7\53\4\0\1\53\4\0\14\53\1\u0109\3\53"+
"\1\0\12\53\1\0\5\53\6\0\7\53\4\0\1\53"+
"\4\0\20\53\1\0\12\53\1\0\4\53\1\u010a\6\0"+
"\7\53\4\0\1\53\4\0\13\53\1\u010b\4\53\1\0"+
"\12\53\1\0\5\53\6\0\7\53\4\0\1\53\4\0"+
"\13\53\1\u010c\4\53\1\0\12\53\1\0\5\53\6\0"+
"\7\53\4\0\1\53\4\0\20\53\1\0\3\53\1\u010d"+
"\6\53\1\0\5\53";
/**
* The transition table of the DFA
*/
final private static int yytrans [] = yy_unpack(yy_packed);
/* error codes */
final private static int YY_UNKNOWN_ERROR = 0;
// final private static int YY_ILLEGAL_STATE = 1;
final private static int YY_NO_MATCH = 2;
final private static int YY_PUSHBACK_2BIG = 3;
/* error messages for the codes above */
final private static String YY_ERROR_MSG[] = {
"Unkown internal scanner error", //$NON-NLS-1$
"Internal error: unknown state", //$NON-NLS-1$
"Error: could not match input", //$NON-NLS-1$
"Error: pushback value was too large" //$NON-NLS-1$
};
/**
* YY_ATTRIBUTE[aState] contains the attributes of state <code>aState</code>
*/
private final static byte YY_ATTRIBUTE[] = {
1, 0, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 9,
1, 9, 1, 1, 9, 9, 1, 1, 1, 1, 1, 1, 1, 1, 9, 1,
1, 1, 1, 9, 1, 1, 1, 1, 1, 1, 1, 1, 9, 1, 1, 1,
1, 9, 1, 1, 1, 1, 1, 9, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 9,
1, 1, 1, 1, 1, 1, 9, 9, 1, 9, 9, 1, 0, 1, 1, 1,
1, 0, 0, 0, 9, 1, 1, 9, 9, 0, 0, 0, 9, 0, 0, 9,
0, 0, 0, 9, 0, 0, 0, 0, 0, 0, 0, 9, 0, 0, 0, 0,
1, 0, 0, 9, 1, 0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 9,
0, 0, 0, 0, 0, 9, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0,
9, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 9, 1, 1, 9,
9, 9, 1, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 1,
0, 1, 0, 1, 9, 0, 1, 1, 9, 1, 1, 0, 0, 0, 0, 0,
0, 0, 1, 0, 1, 0, 1, 9, 1, 0, 0, 0, 0, 0, 1, 1,
0, 1, 0, 0, 0, 9, 9, 1, 1, 0, 1, 9, 9, 9, 1, 1,
0, 1, 1, 1, 9, 1, 1, 1, 1, 1, 1, 1, 1
};
/** the input device */
private java.io.Reader yy_reader;
/** the current state of the DFA */
private int yy_state;
/** the current lexical state */
private int yy_lexical_state = YYINITIAL;
/** this buffer contains the current text to be matched and is
the source of the yytext() string */
private char yy_buffer[] = new char[16384];
/** the textposition at the last accepting state */
private int yy_markedPos;
/** the current text position in the buffer */
private int yy_currentPos;
/** startRead marks the beginning of the yytext() string in the buffer */
private int yy_startRead;
/** endRead marks the last character in the buffer, that has been read
from input */
private int yy_endRead;
/** number of newlines encountered up to the start of the matched text */
// private int yyline;
/** the number of characters up to the start of the matched text */
private int yychar;
/**
* the number of characters from the last newline up to the start of the
* matched text
*/
// private int yycolumn;
/**
* yy_atBOL == true <=> the scanner is currently at the beginning of a line
*/
// private boolean yy_atBOL;
/** yy_atEOF == true <=> the scanner has returned a value for EOF */
private boolean yy_atEOF;
/** denotes if the user-EOF-code has already been executed */
private boolean yy_eof_done;
/* user code: */
private int fTokenCount = 0;
// required holders for white-space compacting
private boolean fShouldLoadBuffered = false;
private String fBufferedContext = null;
private int fBufferedStart = 1;
private int fBufferedLength = 0;
private String f_context = null;
// state stack for handling embedded regions
private IntStack fStateStack = new IntStack();
private String context = null;
private int start = 0;
private int textLength = 0;
private int length = 0;
// offset for tracking position specific block tags
private int fOffset = 0;
// the name of the current tag being opened
private String fCurrentTagName = null;
// the list of tag name BlockMarkers
private List fBlockMarkers = new ArrayList();
// required to not seek text blocks on an end tag
private boolean fIsBlockingEnabled = false;
private boolean fIsCaseSensitiveBlocking = true;
private XMLParserRegionFactory fRegionFactory = new XMLParserRegionFactory();
/**
* user method
*/
public final void addBlockMarker(BlockMarker marker) {
if(containsTagName(marker.getTagName()))
return;
fBlockMarkers.add(marker);
}
/**
* user method
*/
public final void removeBlockMarker(BlockMarker marker) {
fBlockMarkers.remove(marker);
}
/**
* user method
*/
public final void removeBlockMarker(String tagname) {
if (fBlockMarkers != null) {
Iterator blocks = fBlockMarkers.iterator();
while (blocks.hasNext()) {
if (((BlockMarker) blocks.next()).getTagName().equals(tagname))
blocks.remove();
}
}
}
/* user method */
public final boolean isCaseSensitiveBlocking() {
return fIsCaseSensitiveBlocking;
}
/* user method */
public final void setCaseSensitiveBlocking(boolean newValue) {
fIsCaseSensitiveBlocking = newValue;
}
/* user method */
public boolean getBlockMarkerCaseSensitivity() {
return getBlockMarkerCaseSensitivity(fCurrentTagName);
}
/* user method */
public boolean getBlockMarkerCaseSensitivity(String name) {
Iterator iterator = fBlockMarkers.iterator();
while(iterator.hasNext()) {
BlockMarker marker = (BlockMarker)iterator.next();
boolean casesensitive = marker.isCaseSensitive();
if(casesensitive && marker.getTagName().equals(name))
return casesensitive;
else if(!casesensitive && marker.getTagName().equalsIgnoreCase(name))
return casesensitive;
}
return true;
}
/* user method */
public String getBlockMarkerContext() {
return getBlockMarkerContext(fCurrentTagName);
}
/* user method */
public String getBlockMarkerContext(String name) {
Iterator iterator = fBlockMarkers.iterator();
while(iterator.hasNext()) {
BlockMarker marker = (BlockMarker)iterator.next();
if(marker.getTagName().equals(name))
return marker.getContext();
}
return BLOCK_TEXT;
}
/* user method */
public List getBlockMarkers() {
return fBlockMarkers;
}
/* user method */
public final int getOffset() {
return fOffset + yychar;
}
private final boolean isBlockMarker() {
return isBlockMarker(fCurrentTagName);
}
private final boolean isBlockMarker(String tagName) {
if (!fIsBlockingEnabled)
return false;
return containsTagName(tagName);
}
/**
* user method
*/
public final void beginBlockTagScan(String newTagName) {
beginBlockMarkerScan(newTagName, BLOCK_TEXT);
}
/**
* user method
*
* Special tokenizer setup. Allows tokenization to be initiated at the
* start of a text block within a "newTagName" tag.
*
* Example:
* Tokenizer toker = new Tokenizer();
* toker.setCaseSensitiveBlocking(false);
* toker.reset(new java.io.StringReader("afiuhqwkejhtasihgalkwhtq</scripter></scr></script>asgdasga"));
* toker.beginBlockMarkerScan("script", BLOCK_TEXT);
* toker.getRegions();
*
* Returns:
* BLOCK_TEXT: 0-40
* XML_END_TAG_OPEN: 41-42
* XML_TAG_NAME: 43-48
* XML_TAG_CLOSE: 49-49
* XML_CONTENT: 50-57
*
*/
public final void beginBlockMarkerScan(String newTagName, String blockcontext) {
yybegin(ST_BLOCK_TAG_SCAN);
fCurrentTagName = newTagName;
}
/**
* Method doScan.
*
* Returns a context region for all of the text from the current position upto the end of input or
* to right *before* the first occurence of searchString
*
* @param searchString - target string to search for ex.: "-->", "</tagname"
* @param requireTailSeparator - whether the target must be immediately followed by whitespace or '>'
* @param context - the context of the scanned region if non-zero length
* @param exitState - the state to go to if the region was of non-zero length
* @param abortState - the state to go to if the searchString was found immediately
* @return String - the context found: the desired context on a non-zero length match, the abortContext on immediate success
* @throws IOException
*/
private final String doScan(String searchString, boolean requireTailSeparator, String searchContext, int exitState, int immediateFallbackState) throws IOException {
boolean stillSearching = true;
// Disable further block (probably)
fIsBlockingEnabled = false;
int searchStringLength = searchString.length();
int n = 0;
char lastCheckChar;
int i;
boolean same = false;
while (stillSearching) {
n = 0;
// Ensure that enough data from the input exists to compare against the search String.
n = yy_advance();
while(n != YYEOF && yy_currentPos < searchStringLength)
n = yy_advance();
// If the input was too short or we've exhausted the input, stop immediately.
if (n == YYEOF) {
stillSearching = false;
}
else {
same = true;
// Ensure that we've not encountered a complete block (<%%>) that was *shorter* than the closeTagString and
// thus found twice at current-targetLength [since the first scan would have come out this far anyway].
// Check the characters in the target versus the last targetLength characters read from the buffer
// and see if it matches
// safety check for array accesses (yy_currentPos is the *last* character we can check against)
if(yy_currentPos >= searchStringLength && yy_currentPos <= yy_buffer.length) {
for(i = 0; i < searchStringLength; i++) {
if(same && fIsCaseSensitiveBlocking)
same = yy_buffer[i + yy_currentPos - searchStringLength] == searchString.charAt(i);
else if(same && !fIsCaseSensitiveBlocking)
same = Character.toLowerCase(yy_buffer[i + yy_currentPos - searchStringLength]) == Character.toLowerCase(searchString.charAt(i));
}
}
// safety check failed; no match is possible right now
else {
same = false;
}
if (same && requireTailSeparator && yy_currentPos < yy_buffer.length) {
// Additional check for close tags to ensure that targetString="</script" doesn't match
// "</scriptS"
lastCheckChar = yy_buffer[yy_currentPos];
// Succeed on "</script>" and "</script "
if(lastCheckChar == '>' || Character.isWhitespace(lastCheckChar))
stillSearching = false;
}
else {
stillSearching = !same || (yy_currentPos < yy_startRead + searchStringLength);
}
}
}
if (n != YYEOF || same) {
// We've stopped short of the end or definitely found a match
yy_markedPos = yy_currentPos - searchStringLength;
yy_currentPos = yy_markedPos + 1;
// If the searchString occurs at the very beginning of what would have
// been a Block, resume scanning normally immediately
if (yy_markedPos == yy_startRead) {
yybegin(immediateFallbackState);
return primGetNextToken();
}
}
else {
// We ran through the rest of the input
yy_markedPos = yy_currentPos;
yy_currentPos++;
}
yybegin(exitState);
// If the ending occurs at the very beginning of what would have
// been a Block, resume scanning normally immediately
if(yy_markedPos == yy_startRead)
return primGetNextToken();
return searchContext;
}
/**
* user method
*
* A generic lookahead-like operation
*/
private final String doBlockScan(String target, String targetContext, int immediateFallbackState) throws IOException {
return doScan(target, false, targetContext, immediateFallbackState, immediateFallbackState);
}
/**
* user method
* does a lookahead for the current tag name
*/
private final String doBlockTagScan() throws IOException {
fIsCaseSensitiveBlocking = getBlockMarkerCaseSensitivity();
return doScan("</" + fCurrentTagName, true, getBlockMarkerContext(fCurrentTagName), YYINITIAL, YYINITIAL);
}
/**
* user method
*
* Converts the raw context String returned by the primGetNextToken()
* method into a full ITextRegion by pulling in values for the
* current offset within the scanning text.
*
* Returns null when EOF is encountered and attaches intermittently
* discovered whitespace onto the end of useful regions.
*
* Note that this algorithm caches the token following the one being returned
* so that whitespace can be collapsed.
*/
public final ITextRegion getNextToken() throws IOException {
// load the starting non-whitespace token (assume that it is so)
if (fShouldLoadBuffered) {
context = fBufferedContext;
start = fBufferedStart;
textLength = length = fBufferedLength;
fShouldLoadBuffered = false;
}
else {
context = primGetNextToken();
if (context == XML_TAG_NAME) {
if(containsTagName(yy_buffer, yy_startRead, yy_markedPos-yy_startRead))
fCurrentTagName = yytext();
else
fCurrentTagName = null;
}
else if (context == XML_TAG_OPEN) {
fIsBlockingEnabled = true;
}
else if (context == XML_END_TAG_OPEN) {
fIsBlockingEnabled = false;
}
start = yychar;
textLength = length = yylength();
if (yy_atEOF) {
fTokenCount++;
return null;
}
}
// store the next token
f_context = primGetNextToken();
if (f_context == XML_TAG_NAME) {
if(containsTagName(yy_buffer, yy_startRead, yy_markedPos-yy_startRead))
fCurrentTagName = yytext();
else
fCurrentTagName = null;
}
else if (f_context == XML_TAG_OPEN) {
fIsBlockingEnabled = true;
}
else if (f_context == XML_END_TAG_OPEN) {
fIsBlockingEnabled = false;
}
fBufferedContext = f_context;
fBufferedStart = yychar;
fBufferedLength = yylength();
fShouldLoadBuffered = true;
if (fBufferedContext == WHITE_SPACE) {
fShouldLoadBuffered = false;
length += fBufferedLength;
}
if (context == null) {
// EOF
if (Debug.debugTokenizer) {
System.out.println(getClass().getName() + " discovered " + fTokenCount + " tokens."); //$NON-NLS-2$//$NON-NLS-1$
}
return null;
}
fTokenCount++;
return fRegionFactory.createToken(context, start, textLength, length, null, fCurrentTagName);
}
/* user method */
public HTMLTokenizer(){
super();
}
/* user method */
public HTMLTokenizer(char[] charArray){
this(new CharArrayReader(charArray));
}
/* user method */
public void reset(char[] charArray) {
reset(new CharArrayReader(charArray), 0);
}
/* user method */
public void reset(char[] charArray, int newOffset) {
reset(new CharArrayReader(charArray), newOffset);
}
/* user method */
public void reset(java.io.InputStream in) {
reset(new java.io.InputStreamReader(in), 0);
}
/* user method */
public void reset(java.io.InputStream in, int newOffset) {
reset(new java.io.InputStreamReader(in), newOffset);
}
/* user method */
public void reset(java.io.Reader in) {
reset(in, 0);
}
/**
* user method *
*
* Reset internal counters and vars to "newly created" values, in the hopes
* that resetting a pre-existing tokenizer is faster than creating a new one.
*
* This method contains code blocks that were essentially duplicated from the
* <em>generated</em> output of this specification before this method was
* added. Those code blocks were under the above copyright.
*/
public void reset(java.io.Reader in, int newOffset) {
if (Debug.debugTokenizer) {
System.out.println("resetting tokenizer");//$NON-NLS-1$
}
fOffset = newOffset;
/* the input device */
yy_reader = in;
/* the current state of the DFA */
yy_state = 0;
/* the current lexical state */
yy_lexical_state = YYINITIAL;
/* this buffer contains the current text to be matched and is
the source of the yytext() string */
java.util.Arrays.fill(yy_buffer, (char)0);
/* the textposition at the last accepting state */
yy_markedPos = 0;
/* the current text position in the buffer */
yy_currentPos = 0;
/* startRead marks the beginning of the yytext() string in the buffer */
yy_startRead = 0;
/**
* endRead marks the last character in the buffer, that has been read
* from input
*/
yy_endRead = 0;
/* number of newlines encountered up to the start of the matched text */
//yyline = 0;
/* the number of characters up to the start of the matched text */
yychar = 0;
/* yy_atEOF == true <=> the scanner has returned a value for EOF */
yy_atEOF = false;
/* denotes if the user-EOF-code has already been executed */
yy_eof_done = false;
/* user vars: */
fTokenCount = 0;
fShouldLoadBuffered = false;
fBufferedContext = null;
fBufferedStart = 1;
fBufferedLength = 0;
fStateStack = new IntStack();
context = null;
start = 0;
textLength = 0;
length = 0;
}
/**
* user method
*
*/
public BlockTokenizer newInstance() {
HTMLTokenizer newInstance = new HTMLTokenizer();
// global tagmarkers can be shared; they have no state and
// are never destroyed (e.g. 'release')
for(int i = 0; i < fBlockMarkers.size(); i++) {
BlockMarker blockMarker = (BlockMarker) fBlockMarkers.get(i);
if(blockMarker.isGlobal())
newInstance.addBlockMarker(blockMarker);
}
return newInstance;
}
/* user method */
private final String scanXMLCommentText() throws IOException {
// Scan for '-->' and return the text up to that point as
// XML_COMMENT_TEXT unless the string occurs IMMEDIATELY, in which
// case change to the ST_XML_COMMENT_END state and return the next
// context as usual.
return doScan("-->", false, XML_COMMENT_TEXT, ST_XML_COMMENT_END, ST_XML_COMMENT_END);
}
/**
* 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 HTMLTokenizer(java.io.Reader in) {
this.yy_reader = 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 HTMLTokenizer(java.io.InputStream in) {
this(new java.io.InputStreamReader(in));
}
/**
* Unpacks the compressed DFA transition table.
*
* @param packed the packed transition table
* @return the unpacked transition table
*/
private static int [] yy_unpack(String packed) {
int [] trans = new int[10175];
int i = 0; /* index in packed string */
int j = 0; /* index in unpacked array */
while (i < 3126) {
int count = packed.charAt(i++);
int value = packed.charAt(i++);
value--;
do trans[j++] = value; while (--count > 0);
}
return trans;
}
/**
* Unpacks the compressed character translation table.
*
* @param packed the packed character translation table
* @return the unpacked character translation table
*/
private static char [] yy_unpack_cmap(String packed) {
char [] map = new char[0x10000];
int i = 0; /* index in packed string */
int j = 0; /* index in unpacked array */
while (i < 1372) {
int count = packed.charAt(i++);
char value = packed.charAt(i++);
do map[j++] = value; while (--count > 0);
}
return map;
}
/**
* Gets the next input character.
*
* @return the next character of the input stream, EOF if the
* end of the stream is reached.
* @exception IOException if any I/O-Error occurs
*/
private int yy_advance() throws java.io.IOException {
/* standard case */
if (yy_currentPos < yy_endRead) return yy_buffer[yy_currentPos++];
/* if the eof is reached, we don't need to work hard */
if (yy_atEOF) return YYEOF;
/* otherwise: need to refill the buffer */
/* first: make room (if you can) */
if (yy_startRead > 0) {
System.arraycopy(yy_buffer, yy_startRead,
yy_buffer, 0,
yy_endRead-yy_startRead);
/* translate stored positions */
yy_endRead-= yy_startRead;
yy_currentPos-= yy_startRead;
yy_markedPos-= yy_startRead;
yy_startRead = 0;
}
/* is the buffer big enough? */
if (yy_currentPos >= yy_buffer.length) {
/* if not: blow it up */
char newBuffer[] = new char[yy_currentPos*2];
System.arraycopy(yy_buffer, 0, newBuffer, 0, yy_buffer.length);
yy_buffer = newBuffer;
}
/* finally: fill the buffer with new input */
int numRead = yy_reader.read(yy_buffer, yy_endRead,
yy_buffer.length-yy_endRead);
if ( numRead == -1 ) return YYEOF;
yy_endRead+= numRead;
return yy_buffer[yy_currentPos++];
}
/**
* Closes the input stream.
*/
final public void yyclose() throws java.io.IOException {
yy_atEOF = true; /* indicate end of file */
yy_endRead = yy_startRead; /* invalidate buffer */
yy_reader.close();
}
/**
* Returns the current lexical state.
*/
final public int yystate() {
return yy_lexical_state;
}
/**
* Enters a new lexical state
*
* @param newState the new lexical state
*/
final public void yybegin(int newState) {
yy_lexical_state = newState;
}
/**
* Returns the text matched by the current regular expression.
*/
final public String yytext() {
return new String( yy_buffer, yy_startRead, yy_markedPos-yy_startRead );
}
/**
* Returns the length of the matched text region.
*/
final public int yylength() {
return yy_markedPos-yy_startRead;
}
/**
* Reports an error that occured while scanning - from the SED JFlex skeleton
*
* @param errorCode the code of the errormessage to display
*/
private void yy_ScanError(int errorCode) {
try {
Logger.log(Logger.ERROR, YY_ERROR_MSG[errorCode]);
}
catch (ArrayIndexOutOfBoundsException e) {
Logger.log(Logger.ERROR, YY_ERROR_MSG[YY_UNKNOWN_ERROR]);
}
// DO NOT EXIT the VM on an error
// System.exit(1);
}
/**
* 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()!
*/
void yypushback(int number) {
if ( number > yylength() )
yy_ScanError(YY_PUSHBACK_2BIG);
yy_markedPos -= number;
}
/**
* user method - skeleton.sed
*/
protected final boolean containsTagName(char[] markerTagName, int offset, int tagnameLength) {
for(int j = 0; j < fBlockMarkers.size(); j++) {
BlockMarker marker = (BlockMarker)fBlockMarkers.get(j);
if(marker.getTagName().length() == tagnameLength) {
boolean matchesSoFar = true;
for(int i = 0; i < tagnameLength && matchesSoFar; i++) {
if(marker.isCaseSensitive()) {
if(marker.getTagName().charAt(i) != markerTagName[i + offset])
matchesSoFar = false;
}
else {
if(Character.toLowerCase(marker.getTagName().charAt(i)) != Character.toLowerCase(markerTagName[i + offset]))
matchesSoFar = false;
}
}
if(matchesSoFar)
return true;
}
}
return false;
}
/**
* user method - skeleton.sed
*
* Return ALL of the regions scannable within the remaining text
* Note: for verification use
*/
public final List getRegions() {
List tokens = new ArrayList();
ITextRegion region = null;
try {
region = getNextToken();
while(region != null) {
if (region != null) {
tokens.add(region);
}
region = getNextToken();
}
}
catch (StackOverflowError e) {
Logger.logException(getClass().getName()+": input could not be tokenized correctly at position " + getOffset(), e);//$NON-NLS-1$
throw e;
}
catch (Exception e) {
// Since this is convenience method and NOT the recommended
// way of getting tokens, many errors are simply hidden
Logger.logException("Exception not handled retrieving regions: " + e.getLocalizedMessage(), e);//$NON-NLS-1$
}
return tokens;
}
/**
* user method - skeleton.sed
*/
private final void dump(String s) {
if (Debug.debugTokenizer) {
System.out.println(s + " (" + yychar + "-" + //$NON-NLS-2$//$NON-NLS-1$
(yylength() + yychar) + "):\'" +//$NON-NLS-1$
StringUtils.escape(yytext()) + "\'");//$NON-NLS-1$
}
}
/* user method - skeleton.sed */
public final boolean isEOF() {
return yy_atEOF;
}
/* user method - skeleton.sed */
protected final boolean containsTagName(String markerTagName) {
Iterator blocks = fBlockMarkers.iterator();
while(blocks.hasNext()) {
BlockMarker marker = (BlockMarker)blocks.next();
if(marker.isCaseSensitive()) {
if(marker.getTagName().equals(markerTagName))
return true;
}
else {
if(marker.getTagName().equalsIgnoreCase(markerTagName))
return true;
}
}
return false;
}
/**
* Contains user EOF-code, which will be executed exactly once,
* when the end of file is reached
*/
private void yy_do_eof() {
if (!yy_eof_done) {
yy_eof_done = true;
// do nothing, this is the downstream parser's job
}
}
/**
* 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 IOException if any I/O-Error occurs
*/
public String primGetNextToken() throws java.io.IOException {
int yy_input;
int yy_action;
while (true) {
yychar+= yylength();
yy_action = -1;
yy_currentPos = yy_startRead = yy_markedPos;
yy_state = yy_lexical_state;
yy_forAction: {
while (true) {
yy_input = yy_advance();
if ( yy_input == YYEOF ) break yy_forAction;
int yy_next = yytrans[ yy_rowMap[yy_state] + yycmap[yy_input] ];
if (yy_next == -1) break yy_forAction;
yy_state = yy_next;
int yy_attributes = YY_ATTRIBUTE[yy_state];
if ( (yy_attributes & 1) > 0 ) {
yy_action = yy_state;
yy_markedPos = yy_currentPos;
if ( (yy_attributes & 8) > 0 ) break yy_forAction;
}
}
}
switch (yy_action) {
case 268:
{
if(Debug.debugTokenizer)
dump("XSL processing instruction target");//$NON-NLS-1$
yybegin(ST_XML_PI_ATTRIBUTE_NAME);
return XML_TAG_NAME;
}
case 270: break;
case 260:
case 262:
case 263:
{
if(Debug.debugTokenizer)
dump("\nCDATA start");//$NON-NLS-1$
fStateStack.push(yystate());
yybegin(ST_CDATA_TEXT);
return XML_CDATA_OPEN;
}
case 271: break;
case 253:
{
if(Debug.debugTokenizer)
dump("element");//$NON-NLS-1$
yybegin(ST_XML_ELEMENT_DECLARATION);
return XML_ELEMENT_DECLARATION;
}
case 272: break;
case 252:
{
if(Debug.debugTokenizer)
dump("attlist");//$NON-NLS-1$
yybegin(ST_XML_ATTLIST_DECLARATION);
return XML_ATTLIST_DECLARATION;
}
case 273: break;
case 251:
{
if(Debug.debugTokenizer)
dump("doctype");//$NON-NLS-1$
yybegin(ST_XML_DOCTYPE_DECLARATION);
return XML_DOCTYPE_DECLARATION;
}
case 274: break;
case 246:
{
if(Debug.debugTokenizer)
dump("doctype external id");//$NON-NLS-1$
yybegin(ST_XML_DOCTYPE_ID_PUBLIC);
return XML_DOCTYPE_EXTERNAL_ID_PUBLIC;
}
case 275: break;
case 245:
{
if(Debug.debugTokenizer)
dump("doctype external id");//$NON-NLS-1$
yybegin(ST_XML_DOCTYPE_ID_SYSTEM);
return XML_DOCTYPE_EXTERNAL_ID_SYSTEM;
}
case 276: break;
case 216:
{
if(Debug.debugTokenizer)
dump("\nCharRef");//$NON-NLS-1$
return XML_CHAR_REFERENCE;
}
case 277: break;
case 212:
{
if(Debug.debugTokenizer)
dump("\ncomment start");//$NON-NLS-1$
yybegin(ST_XML_COMMENT);
return XML_COMMENT_OPEN;
}
case 278: break;
case 194:
case 195:
{
if(Debug.debugTokenizer)
dump("XML processing instruction target");//$NON-NLS-1$
yybegin(ST_XML_PI_ATTRIBUTE_NAME);
return XML_TAG_NAME;
}
case 279: break;
case 193:
{
if(Debug.debugTokenizer)
dump("comment end");//$NON-NLS-1$
yybegin(YYINITIAL);
return XML_COMMENT_CLOSE;
}
case 280: break;
case 192:
{
if(Debug.debugTokenizer)
dump("CDATA end");//$NON-NLS-1$
yybegin(fStateStack.pop());
return XML_CDATA_CLOSE;
}
case 281: break;
case 191:
{
if(Debug.debugTokenizer)
dump("\nPEReference");//$NON-NLS-1$
return XML_PE_REFERENCE;
}
case 282: break;
case 188:
{
if(Debug.debugTokenizer)
dump("\nEntityRef");//$NON-NLS-1$
return XML_ENTITY_REFERENCE;
}
case 283: break;
case 139:
case 144:
case 156:
{
return XML_DOCTYPE_INTERNAL_SUBSET;
}
case 284: break;
case 127:
{
yybegin(YYINITIAL);
if(Debug.debugTokenizer)
dump("empty tag close");//$NON-NLS-1$
return XML_EMPTY_TAG_CLOSE;
}
case 285: break;
case 120:
{
if(Debug.debugTokenizer)
dump("XML processing instruction end");//$NON-NLS-1$
yybegin(YYINITIAL);
return XML_PI_CLOSE;
}
case 286: break;
case 119:
{
// ended with nothing inside
yybegin(YYINITIAL);
return XML_PI_CLOSE;
}
case 287: break;
case 52:
case 54:
case 55:
case 56:
case 124:
{
if(Debug.debugTokenizer)
dump("XML processing instruction attribute value");//$NON-NLS-1$
yybegin(ST_XML_PI_ATTRIBUTE_NAME);
return XML_TAG_ATTRIBUTE_VALUE;
}
case 288: break;
case 51:
{
if(Debug.debugTokenizer)
dump("XML processing instruction '='");//$NON-NLS-1$
yybegin(ST_XML_PI_ATTRIBUTE_VALUE);
return XML_TAG_ATTRIBUTE_EQUALS;
}
case 289: break;
case 50:
{
if(Debug.debugTokenizer)
dump("XML processing instruction attribute name");//$NON-NLS-1$
yybegin(ST_XML_PI_EQUALS);
return XML_TAG_ATTRIBUTE_NAME;
}
case 290: break;
case 46:
case 47:
case 48:
{
// block scan until close is found
return doScan("?>", false, XML_PI_CONTENT, ST_XML_PI_TAG_CLOSE, ST_XML_PI_TAG_CLOSE);
}
case 291: break;
case 45:
{
yybegin(ST_PI_CONTENT);
return WHITE_SPACE;
}
case 292: break;
case 42:
case 43:
case 44:
case 117:
case 118:
case 218:
case 232:
case 241:
case 250:
case 257:
case 261:
case 264:
case 265:
case 266:
case 267:
{
if(Debug.debugTokenizer)
dump("processing instruction target");//$NON-NLS-1$
yybegin(ST_PI_WS);
return XML_TAG_NAME;
}
case 293: break;
case 37:
case 38:
{
if(Debug.debugTokenizer)
dump("comment content");//$NON-NLS-1$
return scanXMLCommentText();
}
case 294: break;
case 36:
{
if(Debug.debugTokenizer)
dump("LINE FEED");//$NON-NLS-1$
return WHITE_SPACE;
}
case 295: break;
case 31:
case 32:
{
if(Debug.debugTokenizer)
dump("CDATA text");//$NON-NLS-1$
String blockContext = doBlockScan("]]>", XML_CDATA_TEXT, ST_CDATA_END);//$NON-NLS-1$
if(blockContext == XML_CDATA_TEXT)
yybegin(ST_CDATA_END);
return blockContext;
}
case 296: break;
case 0:
case 27:
case 109:
case 110:
case 111:
case 186:
case 187:
case 189:
case 190:
case 214:
case 215:
case 217:
case 230:
case 231:
{
if(Debug.debugTokenizer)
dump("\nXML content");//$NON-NLS-1$
return XML_CONTENT;
}
case 297: break;
case 5:
case 8:
case 9:
case 10:
case 13:
case 14:
case 15:
case 16:
case 17:
case 18:
case 19:
case 20:
case 21:
case 22:
case 24:
case 41:
{
if(Debug.debugTokenizer)
dump("white space");//$NON-NLS-1$
return WHITE_SPACE;
}
case 298: break;
case 12:
case 58:
{
if(Debug.debugTokenizer)
dump("inappropriate tag name");//$NON-NLS-1$
yybegin(YYINITIAL);
return XML_CONTENT;
}
case 299: break;
case 23:
case 93:
case 94:
case 172:
case 207:
case 226:
case 238:
case 247:
case 254:
case 258:
{
if(Debug.debugTokenizer)
dump("elementdecl contentspec");//$NON-NLS-1$
return XML_ELEMENT_DECL_CONTENT;
}
case 300: break;
case 25:
case 100:
case 101:
case 183:
case 211:
case 228:
case 239:
case 248:
case 255:
case 259:
{
if(Debug.debugTokenizer)
dump("attlist contentspec");//$NON-NLS-1$
return XML_ATTLIST_DECL_CONTENT;
}
case 301: break;
case 28:
case 59:
case 70:
{
if(Debug.debugTokenizer)
dump("\nstart tag open");//$NON-NLS-1$
yybegin(ST_XML_TAG_NAME);
return XML_TAG_OPEN;
}
case 302: break;
case 29:
case 33:
case 34:
case 35:
case 39:
case 40:
case 49:
case 53:
case 57:
case 61:
case 67:
case 72:
case 73:
case 74:
case 75:
case 77:
case 78:
case 80:
case 85:
case 90:
case 97:
{
if (Debug.debugTokenizer)
System.out.println("!!!unexpected!!!: \"" + yytext() + "\":" + //$NON-NLS-2$//$NON-NLS-1$
yychar + "-" + (yychar + yylength()));//$NON-NLS-1$
return UNDEFINED;
}
case 303: break;
case 30:
case 112:
{
if(Debug.debugTokenizer)
dump("non-reference %");//$NON-NLS-1$
return XML_CONTENT;
}
case 304: break;
case 60:
{
if(Debug.debugTokenizer)
dump("tag close");//$NON-NLS-1$
if(isBlockMarker()) {
yybegin(ST_BLOCK_TAG_SCAN);
}
else
yybegin(YYINITIAL);
return XML_TAG_CLOSE;
}
case 305: break;
case 62:
case 63:
{
if(Debug.debugTokenizer)
dump("tag name");//$NON-NLS-1$
yybegin(ST_XML_ATTRIBUTE_NAME);
return XML_TAG_NAME;
}
case 306: break;
case 64:
{
if(Debug.debugTokenizer)
dump("attr name");//$NON-NLS-1$
yybegin(ST_XML_EQUALS);
return XML_TAG_ATTRIBUTE_NAME;
}
case 307: break;
case 65:
{
if(Debug.debugTokenizer)
dump("equals");//$NON-NLS-1$
yybegin(ST_XML_ATTRIBUTE_VALUE);
return XML_TAG_ATTRIBUTE_EQUALS;
}
case 308: break;
case 66:
case 68:
case 69:
case 131:
{
if(Debug.debugTokenizer)
dump("attr value");//$NON-NLS-1$
yybegin(ST_XML_ATTRIBUTE_NAME);
return XML_TAG_ATTRIBUTE_VALUE;
}
case 309: break;
case 71:
{
if(Debug.debugTokenizer)
dump("declaration end");//$NON-NLS-1$
if (Debug.debugTokenizer) {
if(fStateStack.peek()!=YYINITIAL)
System.out.println("end embedded region");//$NON-NLS-1$
}
yybegin(fStateStack.pop());
return XML_DECLARATION_CLOSE;
}
case 310: break;
case 76:
{
if(Debug.debugTokenizer)
dump("doctype type");//$NON-NLS-1$
yybegin(ST_XML_DOCTYPE_EXTERNAL_ID);
return XML_DOCTYPE_NAME;
}
case 311: break;
case 79:
case 81:
case 82:
case 83:
case 147:
case 148:
case 151:
case 152:
case 202:
{
if(Debug.debugTokenizer)
dump("doctype public reference");//$NON-NLS-1$
yybegin(ST_XML_DOCTYPE_ID_SYSTEM);
return XML_DOCTYPE_EXTERNAL_ID_PUBREF;
}
case 312: break;
case 84:
case 86:
case 87:
case 88:
case 159:
{
if(Debug.debugTokenizer)
dump("doctype system reference");//$NON-NLS-1$
yybegin(ST_XML_DECLARATION_CLOSE);
return XML_DOCTYPE_EXTERNAL_ID_SYSREF;
}
case 313: break;
case 89:
case 91:
case 92:
case 165:
case 166:
case 169:
case 170:
case 205:
{
if(Debug.debugTokenizer)
dump("elementdecl name");//$NON-NLS-1$
yybegin(ST_XML_ELEMENT_DECLARATION_CONTENT);
return XML_ELEMENT_DECL_NAME;
}
case 314: break;
case 95:
{
if(Debug.debugTokenizer)
dump("elementdecl close");//$NON-NLS-1$
if (Debug.debugTokenizer) {
if(fStateStack.peek()!=YYINITIAL)
System.out.println("end embedded region");//$NON-NLS-1$
}
yybegin(fStateStack.pop());
return XML_DECLARATION_CLOSE;
}
case 315: break;
case 96:
case 98:
case 99:
case 176:
case 177:
case 180:
case 181:
case 209:
{
if(Debug.debugTokenizer)
dump("attlist name");//$NON-NLS-1$
yybegin(ST_XML_ATTLIST_DECLARATION_CONTENT);
return XML_ATTLIST_DECL_NAME;
}
case 316: break;
case 102:
{
if(Debug.debugTokenizer)
dump("attlist close");//$NON-NLS-1$
if (Debug.debugTokenizer) {
if(fStateStack.peek()!=YYINITIAL)
System.out.println("end embedded region");//$NON-NLS-1$
}
yybegin(fStateStack.pop());
return XML_DECLARATION_CLOSE;
}
case 317: break;
case 105:
{
if(Debug.debugTokenizer)
dump("\nend tag open");//$NON-NLS-1$
yybegin(ST_XML_TAG_NAME);
return XML_END_TAG_OPEN;
}
case 318: break;
case 106:
{
if(Debug.debugTokenizer)
dump("\nprocessing instruction start");//$NON-NLS-1$
yybegin(ST_PI);
return XML_PI_OPEN;
}
case 319: break;
case 107:
{
fStateStack.push(yystate());
if(Debug.debugTokenizer)
dump("\ndeclaration start");//$NON-NLS-1$
yybegin(ST_XML_DECLARATION);
return XML_DECLARATION_OPEN;
}
case 320: break;
case 116:
{
if(Debug.debugTokenizer)
dump("processing instruction end");//$NON-NLS-1$
yybegin(YYINITIAL);
return XML_PI_CLOSE;
}
case 321: break;
case 103:
case 104:
{
return doBlockTagScan();
}
case 322: break;
default:
if (yy_input == YYEOF && yy_startRead == yy_currentPos) {
yy_atEOF = true;
yy_do_eof();
return null;
}
else {
yy_ScanError(YY_NO_MATCH);
}
}
}
}
}