org.carrot2.language.ExtendedWhitespaceTokenizerImpl Maven / Gradle / Ivy
Show all versions of carrot2-core Show documentation
// DO NOT EDIT
// Generated by JFlex 1.8.2 http://jflex.de/
// source: src/main/jflex/org/carrot2/language/ExtendedWhitespaceTokenizerImpl.jflex
package org.carrot2.language;
/** JFlex-generated scanner. */
// See https://github.com/jflex-de/jflex/issues/222
@SuppressWarnings("FallThrough")
public final class ExtendedWhitespaceTokenizerImpl {
/** This character denotes the end of file. */
public static final int YYEOF = -1;
/** Initial size of the lookahead buffer. */
private static final int ZZ_BUFFERSIZE = 16384;
// Lexical states.
public static final int YYINITIAL = 0;
/**
* ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l
* ZZ_LEXSTATE[l+1] is the state in the DFA for the lexical state l
* at the beginning of a line
* l is of the form l = 2*k, k a non negative integer
*/
private static final int ZZ_LEXSTATE[] = {
0, 0
};
/**
* Top-level table for translating characters to character classes
*/
private static final int [] ZZ_CMAP_TOP = zzUnpackcmap_top();
private static final String ZZ_CMAP_TOP_PACKED_0 =
"\1\0\5\u0100\1\u0200\2\u0100\1\u0300\1\u0400\1\u0500\1\u0400"+
"\1\u0600\1\u0700\1\u0100\1\u0800\17\u0100\1\u0900\17\u0a00\1\u0b00"+
"\1\u0c00\1\u0a00\1\u0d00\11\u0100\1\u0e00\20\u0a00\122\u0100\14\u0a00"+
"\53\u0100\1\u0f00\10\u1000\31\u0a00\2\u0100\u1005\u0a00";
private static int [] zzUnpackcmap_top() {
int [] result = new int[4352];
int offset = 0;
offset = zzUnpackcmap_top(ZZ_CMAP_TOP_PACKED_0, offset, result);
return result;
}
private static int zzUnpackcmap_top(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;
}
/**
* Second-level tables for translating characters to character classes
*/
private static final int [] ZZ_CMAP_BLOCKS = zzUnpackcmap_blocks();
private static final String ZZ_CMAP_BLOCKS_PACKED_0 =
"\12\0\1\1\2\0\1\2\23\0\1\3\1\0\1\4"+
"\2\5\1\6\1\7\4\5\1\10\1\11\1\12\1\13"+
"\12\14\1\15\1\16\1\0\1\5\1\0\1\3\1\17"+
"\32\20\1\5\1\0\1\5\1\0\1\21\1\22\1\23"+
"\1\24\1\25\1\26\1\27\1\30\1\31\1\32\1\33"+
"\2\20\1\34\1\35\1\36\1\37\1\40\1\20\1\41"+
"\1\42\1\43\1\44\1\45\3\20\1\46\3\0\1\5"+
"\70\0\1\47\10\0\27\50\1\0\37\50\1\0\u0168\50"+
"\12\51\206\50\12\51\152\50\2\47\12\51\166\50\12\51"+
"\166\50\12\51\166\50\12\51\166\50\12\51\167\50\11\51"+
"\166\50\12\51\340\50\12\51\166\50\12\51\146\50\12\51"+
"\266\50\u0240\0\u0150\50\160\0\200\50\200\0\56\50\322\0"+
"\244\50\134\0\u0100\52";
private static int [] zzUnpackcmap_blocks() {
int [] result = new int[4352];
int offset = 0;
offset = zzUnpackcmap_blocks(ZZ_CMAP_BLOCKS_PACKED_0, offset, result);
return result;
}
private static int zzUnpackcmap_blocks(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 DFA states to action switch labels.
*/
private static final int [] ZZ_ACTION = zzUnpackAction();
private static final String ZZ_ACTION_PACKED_0 =
"\1\0\2\1\1\2\1\1\1\3\1\4\4\5\1\4"+
"\2\0\1\6\2\0\1\5\1\6\1\4\2\0\1\6"+
"\5\5\1\6\1\5\1\7\1\4\1\0\1\4\12\6"+
"\1\4\1\10\1\11\1\5\1\12\12\6\4\5\3\4"+
"\12\13\1\4\2\0\1\5\1\0\1\11\1\0\2\5"+
"\1\11\1\14\1\6\2\14\2\6\1\14\1\6\1\14"+
"\1\12\1\0\2\5\12\6\1\10\2\4\1\0\1\5"+
"\5\0";
private static int [] zzUnpackAction() {
int [] result = new int[119];
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\53\0\126\0\201\0\254\0\53\0\327\0\u0102"+
"\0\u012d\0\u0158\0\u0183\0\u01ae\0\u01d9\0\u0204\0\u022f\0\u025a"+
"\0\u0285\0\u02b0\0\u02db\0\u0306\0\u0331\0\u035c\0\u0387\0\u03b2"+
"\0\u03dd\0\u0408\0\u0433\0\u045e\0\u0489\0\u04b4\0\53\0\u04df"+
"\0\u050a\0\u0535\0\u0560\0\u058b\0\u05b6\0\u05e1\0\u060c\0\u0637"+
"\0\u0662\0\u068d\0\u06b8\0\u06e3\0\u070e\0\u0739\0\u0764\0\u078f"+
"\0\u07ba\0\u07e5\0\u0810\0\u083b\0\u0866\0\u0891\0\u08bc\0\u08e7"+
"\0\u0912\0\u093d\0\u0968\0\u035c\0\u0993\0\u09be\0\u09e9\0\u0a14"+
"\0\u0a3f\0\u0a6a\0\u0a95\0\u0ac0\0\u0aeb\0\u0b16\0\u0b41\0\u0b6c"+
"\0\u0b97\0\u0bc2\0\u0bed\0\u0c18\0\u0c43\0\u0c6e\0\u0c99\0\u0cc4"+
"\0\u0cef\0\u03b2\0\u0d1a\0\u0d45\0\u0d70\0\u04b4\0\u0d9b\0\u0a95"+
"\0\u0dc6\0\u0df1\0\u0e1c\0\u0e47\0\u0e72\0\u0e9d\0\u0ec8\0\u0ef3"+
"\0\u0f1e\0\u0f49\0\u0f74\0\u0f9f\0\u0fca\0\u0ff5\0\u1020\0\u104b"+
"\0\u1076\0\u10a1\0\u10cc\0\u10f7\0\u1122\0\u114d\0\u1178\0\u11a3"+
"\0\u11ce\0\u11f9\0\u1224\0\u124f\0\u127a\0\u12a5\0\u12d0";
private static int [] zzUnpackRowMap() {
int [] result = new int[119];
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 =
"\2\2\1\3\1\4\2\2\1\5\3\6\1\4\1\2"+
"\1\7\1\6\1\4\1\2\1\10\1\2\1\6\5\10"+
"\1\11\1\10\1\12\2\10\1\13\11\10\1\4\1\10"+
"\1\14\55\0\1\2\54\0\1\4\6\0\1\4\3\0"+
"\1\4\30\0\1\4\7\0\1\15\7\0\1\15\3\0"+
"\1\15\2\0\24\15\14\0\1\16\1\17\1\20\1\16"+
"\1\7\1\16\1\0\1\21\1\22\1\23\1\0\24\22"+
"\1\0\1\22\1\24\7\0\1\25\1\26\1\0\1\27"+
"\1\30\1\0\1\22\2\0\1\21\1\22\1\23\1\26"+
"\17\22\1\31\4\22\1\0\2\22\7\0\1\25\1\26"+
"\1\0\1\27\1\30\1\0\1\22\2\0\1\21\1\22"+
"\1\23\1\26\17\22\1\31\1\32\3\22\1\0\2\22"+
"\7\0\1\25\1\26\1\0\1\27\1\30\1\0\1\22"+
"\2\0\1\21\1\22\1\23\1\26\17\22\1\31\1\33"+
"\3\22\1\0\2\22\7\0\1\25\1\26\1\0\1\27"+
"\1\30\1\0\1\22\2\0\1\21\1\22\1\23\1\26"+
"\1\34\16\22\1\31\4\22\1\0\2\22\7\0\1\25"+
"\1\26\1\16\1\35\1\36\1\16\1\24\1\16\1\0"+
"\1\21\1\22\1\23\1\26\17\22\1\31\4\22\1\0"+
"\1\22\1\24\5\0\1\15\7\0\1\15\1\0\1\37"+
"\1\0\1\15\2\0\24\15\20\0\1\40\34\0\1\40"+
"\12\0\1\23\1\41\1\0\1\42\2\0\1\21\2\23"+
"\1\0\24\23\1\0\1\23\1\42\15\0\1\42\3\0"+
"\1\43\2\0\1\44\1\45\1\46\1\43\1\47\1\43"+
"\1\50\1\43\1\51\1\43\1\52\1\53\1\54\7\43"+
"\1\0\1\43\1\55\15\0\1\56\3\0\1\56\2\0"+
"\24\56\1\0\2\56\7\0\1\25\1\26\1\0\1\27"+
"\1\41\1\0\1\22\2\0\1\21\1\22\1\23\1\26"+
"\17\22\1\31\4\22\1\0\2\22\12\0\1\23\1\41"+
"\1\0\1\23\2\0\1\21\2\23\1\0\24\23\1\0"+
"\2\23\7\0\1\25\1\26\1\16\1\35\1\20\1\16"+
"\1\24\1\16\1\0\1\21\1\22\1\23\1\26\17\22"+
"\1\31\4\22\1\0\1\22\1\24\15\0\1\25\3\0"+
"\1\57\2\0\24\57\1\0\2\57\21\0\1\60\2\0"+
"\24\60\1\0\2\60\12\0\1\23\1\41\1\0\1\27"+
"\2\0\1\21\1\61\1\23\1\0\24\61\1\0\2\61"+
"\15\0\1\23\3\0\1\62\2\0\1\63\1\64\1\65"+
"\1\62\1\66\1\62\1\67\1\62\1\70\1\62\1\71"+
"\1\72\1\73\7\62\1\0\2\62\7\0\1\25\1\74"+
"\1\0\1\27\1\41\1\0\1\22\2\0\1\21\1\22"+
"\1\23\1\74\17\22\1\31\4\22\1\0\2\22\7\0"+
"\1\25\1\26\1\0\1\27\1\41\1\0\1\22\2\0"+
"\1\21\1\22\1\23\1\26\15\22\1\75\1\22\1\31"+
"\4\22\1\0\2\22\7\0\1\25\1\26\1\0\1\27"+
"\1\41\1\0\1\22\2\0\1\21\1\22\1\23\1\26"+
"\17\22\1\31\1\76\3\22\1\0\2\22\7\0\1\25"+
"\1\26\1\0\1\27\1\41\1\0\1\22\2\0\1\21"+
"\1\22\1\23\1\26\10\22\1\77\6\22\1\31\4\22"+
"\1\0\2\22\12\0\1\23\1\41\1\0\1\100\2\0"+
"\1\21\1\61\1\23\1\0\24\61\1\0\1\61\1\101"+
"\15\0\1\42\3\0\1\62\2\0\1\63\1\64\1\65"+
"\1\62\1\66\1\62\1\67\1\62\1\70\1\62\1\71"+
"\1\72\1\73\7\62\1\0\1\62\1\102\11\0\4\16"+
"\1\40\1\16\33\0\1\40\15\0\1\23\3\0\1\43"+
"\2\0\1\44\1\45\1\46\1\43\1\47\1\43\1\50"+
"\1\43\1\51\1\43\1\52\1\53\1\54\7\43\1\0"+
"\2\43\11\0\1\16\1\17\1\20\1\16\1\42\1\16"+
"\1\0\1\21\2\23\1\0\24\23\1\0\1\23\1\42"+
"\12\0\1\23\1\41\1\0\1\23\2\0\1\21\1\103"+
"\1\23\1\0\24\103\1\0\2\103\12\0\1\23\1\41"+
"\1\0\1\23\2\0\1\21\1\103\1\23\1\0\16\103"+
"\1\104\5\103\1\0\2\103\12\0\1\23\1\41\1\0"+
"\1\23\2\0\1\21\1\103\1\23\1\0\10\103\1\105"+
"\13\103\1\0\2\103\12\0\1\23\1\41\1\0\1\23"+
"\2\0\1\21\1\103\1\23\1\0\14\103\1\106\7\103"+
"\1\0\2\103\12\0\1\23\1\41\1\0\1\23\2\0"+
"\1\21\1\103\1\23\1\0\3\103\1\107\20\103\1\0"+
"\2\103\12\0\1\23\1\41\1\0\1\23\2\0\1\21"+
"\1\103\1\23\1\0\14\103\1\110\7\103\1\0\2\103"+
"\12\0\1\23\1\41\1\0\1\23\2\0\1\21\1\103"+
"\1\23\1\0\13\103\1\111\10\103\1\0\2\103\12\0"+
"\1\23\1\41\1\0\1\23\2\0\1\21\1\103\1\23"+
"\1\0\10\103\1\112\13\103\1\0\2\103\12\0\1\23"+
"\1\41\1\0\1\23\2\0\1\21\1\103\1\23\1\0"+
"\4\103\1\113\17\103\1\0\2\103\12\0\1\23\1\41"+
"\1\0\1\23\2\0\1\21\1\103\1\23\1\0\16\103"+
"\1\114\5\103\1\0\2\103\11\0\1\16\1\17\1\20"+
"\1\16\1\42\1\16\1\0\1\21\1\103\1\23\1\0"+
"\24\103\1\0\1\103\1\115\12\0\1\56\1\21\1\0"+
"\1\56\3\0\2\56\1\0\24\56\1\0\2\56\7\0"+
"\1\25\1\116\4\0\1\57\3\0\1\57\1\0\1\116"+
"\24\57\1\0\2\57\7\0\1\25\1\26\1\0\1\117"+
"\2\0\1\60\3\0\1\60\1\0\1\26\17\60\1\120"+
"\4\60\1\0\2\60\10\0\1\121\1\0\1\27\1\41"+
"\1\0\1\61\2\0\1\21\1\61\1\23\1\121\24\61"+
"\1\0\2\61\12\0\1\23\1\122\1\0\1\23\2\0"+
"\1\21\1\103\1\23\1\0\24\103\1\0\2\103\12\0"+
"\1\23\1\122\1\0\1\23\2\0\1\21\1\103\1\23"+
"\1\0\16\103\1\104\5\103\1\0\2\103\12\0\1\23"+
"\1\122\1\0\1\23\2\0\1\21\1\103\1\23\1\0"+
"\10\103\1\105\13\103\1\0\2\103\12\0\1\23\1\122"+
"\1\0\1\23\2\0\1\21\1\103\1\23\1\0\14\103"+
"\1\106\7\103\1\0\2\103\12\0\1\23\1\122\1\0"+
"\1\23\2\0\1\21\1\103\1\23\1\0\3\103\1\107"+
"\20\103\1\0\2\103\12\0\1\23\1\122\1\0\1\23"+
"\2\0\1\21\1\103\1\23\1\0\14\103\1\110\7\103"+
"\1\0\2\103\12\0\1\23\1\122\1\0\1\23\2\0"+
"\1\21\1\103\1\23\1\0\13\103\1\111\10\103\1\0"+
"\2\103\12\0\1\23\1\122\1\0\1\23\2\0\1\21"+
"\1\103\1\23\1\0\10\103\1\112\13\103\1\0\2\103"+
"\12\0\1\23\1\122\1\0\1\23\2\0\1\21\1\103"+
"\1\23\1\0\4\103\1\113\17\103\1\0\2\103\12\0"+
"\1\23\1\122\1\0\1\23\2\0\1\21\1\103\1\23"+
"\1\0\16\103\1\114\5\103\1\0\2\103\7\0\1\25"+
"\1\26\1\0\1\27\1\41\1\0\1\22\1\123\1\0"+
"\1\21\1\22\1\23\1\26\17\22\1\31\4\22\1\0"+
"\2\22\7\0\1\25\1\26\1\0\1\27\1\41\1\0"+
"\1\22\2\0\1\21\1\22\1\23\1\26\15\22\1\124"+
"\1\22\1\31\4\22\1\0\2\22\7\0\1\25\1\26"+
"\1\0\1\27\1\41\1\0\1\22\2\0\1\21\1\22"+
"\1\23\1\26\11\22\1\125\5\22\1\31\4\22\1\0"+
"\2\22\11\0\1\16\1\17\1\20\1\16\1\100\1\16"+
"\1\0\1\21\1\61\1\23\1\0\24\61\1\0\1\61"+
"\1\101\10\0\1\121\1\16\1\35\1\20\1\16\1\101"+
"\1\16\1\0\1\21\1\61\1\23\1\121\24\61\1\0"+
"\1\61\1\101\11\0\1\16\1\17\1\126\1\16\1\42"+
"\1\16\1\0\1\21\1\103\1\23\1\0\24\103\1\0"+
"\1\103\1\115\4\0\6\127\1\130\1\131\1\127\1\130"+
"\2\127\1\132\2\130\1\0\24\130\1\0\2\130\4\0"+
"\6\127\1\130\1\131\1\127\1\130\2\127\1\132\2\130"+
"\1\0\15\130\1\133\6\130\1\0\2\130\4\0\6\127"+
"\1\130\1\131\1\127\1\130\2\127\1\132\2\130\1\0"+
"\23\130\1\103\1\0\2\130\4\0\6\127\1\130\1\131"+
"\1\127\1\130\2\127\1\132\2\130\1\0\12\130\1\103"+
"\11\130\1\0\2\130\4\0\6\127\1\130\1\131\1\127"+
"\1\130\2\127\1\132\2\130\1\0\21\130\1\103\2\130"+
"\1\0\2\130\4\0\6\127\1\130\1\131\1\127\1\130"+
"\2\127\1\132\2\130\1\0\22\130\1\103\1\130\1\0"+
"\2\130\4\0\6\127\1\130\1\131\1\127\1\130\2\127"+
"\1\132\2\130\1\0\5\130\1\134\16\130\1\0\2\130"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\2\130\1\0\11\130\1\103\12\130\1\0\2\130\4\0"+
"\6\127\1\130\1\131\1\127\1\130\2\127\1\132\2\130"+
"\1\0\20\130\1\103\3\130\1\0\2\130\4\0\6\127"+
"\1\130\1\131\1\127\1\130\2\127\1\132\2\130\1\0"+
"\6\130\1\103\15\130\1\0\2\130\4\0\5\127\1\135"+
"\1\136\1\137\1\135\1\115\1\135\1\127\1\132\2\130"+
"\1\0\24\130\1\0\1\130\1\115\21\0\1\57\2\0"+
"\24\57\1\0\2\57\15\0\1\117\3\0\1\140\2\0"+
"\24\140\1\0\2\140\7\0\1\25\1\74\1\0\1\117"+
"\2\0\1\60\3\0\1\60\1\0\1\74\17\60\1\120"+
"\4\60\1\0\2\60\21\0\1\140\2\0\24\140\1\0"+
"\2\140\14\0\1\141\45\0\1\25\1\26\1\0\1\27"+
"\1\41\1\0\1\22\1\123\1\0\1\21\1\22\1\23"+
"\1\26\17\22\1\142\4\22\1\0\2\22\7\0\1\25"+
"\1\26\1\0\1\27\1\41\1\0\1\22\2\0\1\21"+
"\1\22\1\23\1\26\17\22\1\31\1\143\3\22\1\0"+
"\2\22\4\0\17\127\1\0\24\127\1\0\2\127\4\0"+
"\11\127\1\130\3\127\1\144\1\127\1\0\1\145\1\146"+
"\1\147\1\144\1\150\1\144\1\151\1\144\1\152\1\144"+
"\1\153\1\154\1\155\7\144\1\0\2\144\4\0\11\127"+
"\1\156\3\127\1\156\1\127\1\0\24\156\1\0\2\156"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\2\130\1\0\1\103\23\130\1\0\2\130\4\0\6\127"+
"\1\130\1\131\1\127\1\130\2\127\1\132\2\130\1\0"+
"\14\130\1\103\7\130\1\0\2\130\4\0\11\127\1\157"+
"\5\127\1\0\24\127\1\0\1\127\1\157\4\0\6\127"+
"\1\130\1\131\1\127\1\115\2\127\1\132\2\130\1\0"+
"\24\130\1\0\1\130\1\115\4\0\11\127\1\115\3\127"+
"\1\144\1\127\1\0\1\145\1\146\1\147\1\144\1\150"+
"\1\144\1\151\1\144\1\152\1\144\1\153\1\154\1\155"+
"\7\144\1\0\1\144\1\160\10\0\1\121\1\0\1\117"+
"\2\0\1\140\3\0\1\140\1\0\1\121\24\140\1\0"+
"\2\140\14\0\1\161\45\0\1\25\1\74\1\0\1\27"+
"\1\41\1\0\1\22\1\123\1\0\1\21\1\22\1\23"+
"\1\74\17\22\1\31\4\22\1\0\2\22\7\0\1\25"+
"\1\26\1\0\1\27\1\41\1\0\1\22\2\0\1\21"+
"\1\22\1\23\1\26\14\22\1\162\2\22\1\31\4\22"+
"\1\0\2\22\4\0\6\127\1\130\1\131\1\127\1\130"+
"\2\127\1\132\1\103\1\130\1\0\24\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\16\103\1\104\5\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\10\103\1\105\13\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\14\103\1\106\7\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\3\103\1\107\20\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\14\103\1\110\7\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\13\103\1\111\10\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\10\103\1\112\13\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\4\103\1\113\17\103\1\0\2\103"+
"\4\0\6\127\1\130\1\131\1\127\1\130\2\127\1\132"+
"\1\103\1\130\1\0\16\103\1\114\5\103\1\0\2\103"+
"\4\0\6\127\1\156\1\132\1\127\1\156\3\127\2\156"+
"\1\0\24\156\1\0\2\156\4\0\5\127\4\135\1\157"+
"\1\135\4\127\1\0\24\127\1\0\1\127\1\157\4\0"+
"\5\127\1\135\1\136\1\137\1\135\1\115\1\135\1\127"+
"\1\132\1\103\1\130\1\0\24\103\1\0\1\103\1\115"+
"\15\0\1\163\3\0\1\163\2\0\24\163\1\0\2\163"+
"\7\0\1\25\1\26\1\0\1\27\1\41\1\0\1\22"+
"\1\164\1\0\1\21\1\22\1\23\1\26\17\22\1\31"+
"\4\22\1\0\2\22\12\0\1\163\1\165\1\0\1\163"+
"\3\0\2\163\1\0\24\163\1\0\2\163\15\0\1\166"+
"\3\0\1\166\2\0\24\166\1\0\2\166\15\0\1\163"+
"\3\0\1\167\2\0\24\167\1\0\2\167\12\0\1\166"+
"\1\164\1\0\1\166\2\0\1\21\2\166\1\0\24\166"+
"\1\0\2\166\12\0\1\163\1\165\1\0\1\163\3\0"+
"\1\127\1\163\1\0\24\127\1\0\2\127\1\0";
private static int [] zzUnpackTrans() {
int [] result = new int[4859];
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 code for "Unknown internal scanner error". */
private static final int ZZ_UNKNOWN_ERROR = 0;
/** Error code for "could not match input". */
private static final int ZZ_NO_MATCH = 1;
/** Error code for "pushback value was too large". */
private static final int ZZ_PUSHBACK_2BIG = 2;
/**
* Error messages for {@link #ZZ_UNKNOWN_ERROR}, {@link #ZZ_NO_MATCH}, and
* {@link #ZZ_PUSHBACK_2BIG} respectively.
*/
private static final String ZZ_ERROR_MSG[] = {
"Unknown internal scanner error",
"Error: could not match input",
"Error: pushback value was too large"
};
/**
* ZZ_ATTRIBUTE[aState] contains the attributes of state {@code aState}
*/
private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
private static final String ZZ_ATTRIBUTE_PACKED_0 =
"\1\0\1\11\3\1\1\11\6\1\2\0\1\1\2\0"+
"\3\1\2\0\10\1\1\11\1\1\1\0\54\1\2\0"+
"\1\1\1\0\1\1\1\0\15\1\1\0\17\1\1\0"+
"\1\1\5\0";
private static int [] zzUnpackAttribute() {
int [] result = new int[119];
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;
}
/** Input device. */
private java.io.Reader zzReader;
/** Current state of the DFA. */
private int zzState;
/** Current lexical state. */
private int zzLexicalState = YYINITIAL;
/**
* This buffer contains the current text to be matched and is the source of the {@link #yytext()}
* string.
*/
private char zzBuffer[] = new char[ZZ_BUFFERSIZE];
/** Text position at the last accepting state. */
private int zzMarkedPos;
/** Current text position in the buffer. */
private int zzCurrentPos;
/** Marks the beginning of the {@link #yytext()} string in the buffer. */
private int zzStartRead;
/** Marks the last character in the buffer, that has been read from input. */
private int zzEndRead;
/**
* Whether the scanner is at the end of file.
* @see #yyatEOF
*/
private boolean zzAtEOF;
/**
* The number of occupied positions in {@link #zzBuffer} beyond {@link #zzEndRead}.
*
* When a lead/high surrogate has been read from the input stream into the final
* {@link #zzBuffer} position, this will have a value of 1; otherwise, it will have a value of 0.
*/
private int zzFinalHighSurrogate = 0;
/** Number of newlines encountered up to the start of the matched text. */
@SuppressWarnings("unused")
private int yyline;
/** Number of characters from the last newline up to the start of the matched text. */
@SuppressWarnings("unused")
private int yycolumn;
/** Number of characters up to the start of the matched text. */
private long yychar;
/** Whether the scanner is currently at the beginning of a line. */
@SuppressWarnings("unused")
private boolean zzAtBOL = true;
/** Whether the user-EOF-code has already been executed. */
@SuppressWarnings("unused")
private boolean zzEOFDone;
/* user code: */
public final int yychar()
{
return Math.toIntExact(yychar);
}
/**
* Return the internal token's character buffer.
*/
final char [] yybuffer() {
return zzBuffer;
}
final int yystart() {
return zzStartRead;
}
/**
* Creates a new scanner
*
* @param in the java.io.Reader to read input from.
*/
public ExtendedWhitespaceTokenizerImpl(java.io.Reader in) {
this.zzReader = in;
}
/**
* Translates raw input code points to DFA table row
*/
private static int zzCMap(int input) {
int offset = input & 255;
return offset == input ? ZZ_CMAP_BLOCKS[offset] : ZZ_CMAP_BLOCKS[ZZ_CMAP_TOP[input >> 8] | offset];
}
/**
* Refills the input buffer.
*
* @return {@code false} iff there was new input.
* @exception java.io.IOException if any I/O-Error occurs
*/
private boolean zzRefill() throws java.io.IOException {
/* first: make room (if you can) */
if (zzStartRead > 0) {
zzEndRead += zzFinalHighSurrogate;
zzFinalHighSurrogate = 0;
System.arraycopy(zzBuffer, zzStartRead,
zzBuffer, 0,
zzEndRead - zzStartRead);
/* translate stored positions */
zzEndRead -= zzStartRead;
zzCurrentPos -= zzStartRead;
zzMarkedPos -= zzStartRead;
zzStartRead = 0;
}
/* is the buffer big enough? */
if (zzCurrentPos >= zzBuffer.length - zzFinalHighSurrogate) {
/* if not: blow it up */
char newBuffer[] = new char[zzBuffer.length * 2];
System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length);
zzBuffer = newBuffer;
zzEndRead += zzFinalHighSurrogate;
zzFinalHighSurrogate = 0;
}
/* fill the buffer with new input */
int requested = zzBuffer.length - zzEndRead;
int numRead = zzReader.read(zzBuffer, zzEndRead, requested);
/* not supposed to occur according to specification of java.io.Reader */
if (numRead == 0) {
throw new java.io.IOException(
"Reader returned 0 characters. See JFlex examples/zero-reader for a workaround.");
}
if (numRead > 0) {
zzEndRead += numRead;
if (Character.isHighSurrogate(zzBuffer[zzEndRead - 1])) {
if (numRead == requested) { // We requested too few chars to encode a full Unicode character
--zzEndRead;
zzFinalHighSurrogate = 1;
} else { // There is room in the buffer for at least one more char
int c = zzReader.read(); // Expecting to read a paired low surrogate char
if (c == -1) {
return true;
} else {
zzBuffer[zzEndRead++] = (char)c;
}
}
}
/* potentially more input available */
return false;
}
/* numRead < 0 ==> end of stream */
return true;
}
/**
* Closes the input reader.
*
* @throws java.io.IOException if the reader could not be closed.
*/
public final void yyclose() throws java.io.IOException {
zzAtEOF = true; // indicate end of file
zzEndRead = zzStartRead; // invalidate buffer
if (zzReader != null) {
zzReader.close();
}
}
/**
* 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 cannot be reused (internal
* buffer is discarded and lost). Lexical state is set to {@code ZZ_INITIAL}.
*
*
Internal scan buffer is resized down to its initial length, if it has grown.
*
* @param reader The new input stream.
*/
public final void yyreset(java.io.Reader reader) {
zzReader = reader;
zzEOFDone = false;
yyResetPosition();
zzLexicalState = YYINITIAL;
if (zzBuffer.length > ZZ_BUFFERSIZE) {
zzBuffer = new char[ZZ_BUFFERSIZE];
}
}
/**
* Resets the input position.
*/
private final void yyResetPosition() {
zzAtBOL = true;
zzAtEOF = false;
zzCurrentPos = 0;
zzMarkedPos = 0;
zzStartRead = 0;
zzEndRead = 0;
zzFinalHighSurrogate = 0;
yyline = 0;
yycolumn = 0;
yychar = 0L;
}
/**
* Returns whether the scanner has reached the end of the reader it reads from.
*
* @return whether the scanner has reached EOF.
*/
public final boolean yyatEOF() {
return zzAtEOF;
}
/**
* Returns the current lexical state.
*
* @return 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.
*
* @return the matched text.
*/
public final String yytext() {
return new String(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}
/**
* Returns the character at the given position from the matched text.
*
*
It is equivalent to {@code yytext().charAt(pos)}, but faster.
*
* @param position the position of the character to fetch. A value from 0 to {@code yylength()-1}.
*
* @return the character at {@code position}.
*/
public final char yycharat(int position) {
return zzBuffer[zzStartRead + position];
}
/**
* How many characters were matched.
*
* @return the length of the matched text region.
*/
public final int yylength() {
return zzMarkedPos-zzStartRead;
}
/**
* Reports an error that occurred while scanning.
*
*
In a well-formed scanner (no or only correct usage of {@code 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 error message to display.
*/
private static 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
* {@link #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 int getNextToken() throws java.io.IOException {
int zzInput;
int zzAction;
// cached fields:
int zzCurrentPosL;
int zzMarkedPosL;
int zzEndReadL = zzEndRead;
char[] zzBufferL = zzBuffer;
int [] zzTransL = ZZ_TRANS;
int [] zzRowMapL = ZZ_ROWMAP;
int [] zzAttrL = ZZ_ATTRIBUTE;
while (true) {
zzMarkedPosL = zzMarkedPos;
yychar+= zzMarkedPosL-zzStartRead;
zzAction = -1;
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
zzState = ZZ_LEXSTATE[zzLexicalState];
// set up zzAction for empty match case:
int zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
}
zzForAction: {
while (true) {
if (zzCurrentPosL < zzEndReadL) {
zzInput = Character.codePointAt(zzBufferL, zzCurrentPosL, zzEndReadL);
zzCurrentPosL += Character.charCount(zzInput);
}
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 = Character.codePointAt(zzBufferL, zzCurrentPosL, zzEndReadL);
zzCurrentPosL += Character.charCount(zzInput);
}
}
int zzNext = zzTransL[ zzRowMapL[zzState] + zzCMap(zzInput) ];
if (zzNext == -1) break zzForAction;
zzState = zzNext;
zzAttributes = zzAttrL[zzState];
if ( (zzAttributes & 1) == 1 ) {
zzAction = zzState;
zzMarkedPosL = zzCurrentPosL;
if ( (zzAttributes & 8) == 8 ) break zzForAction;
}
}
}
// store back cached position
zzMarkedPos = zzMarkedPosL;
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
zzAtEOF = true;
return YYEOF;
}
else {
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
case 1:
{ /* ignorable . */ break;
}
// fall through
case 13: break;
case 2:
{ return Tokenizer.TT_PUNCTUATION | Tokenizer.TF_SEPARATOR_SENTENCE;
}
// fall through
case 14: break;
case 3:
{ return Tokenizer.TT_PUNCTUATION;
}
// fall through
case 15: break;
case 4:
{ return Tokenizer.TT_NUMERIC;
}
// fall through
case 16: break;
case 5:
{ return Tokenizer.TT_TERM;
}
// fall through
case 17: break;
case 6:
{ return Tokenizer.TT_FILE;
}
// fall through
case 18: break;
case 7:
{ /* html entities. */ break;
}
// fall through
case 19: break;
case 8:
{ return Tokenizer.TT_EMAIL;
}
// fall through
case 20: break;
case 9:
{ return Tokenizer.TT_ACRONYM;
}
// fall through
case 21: break;
case 10:
{ return Tokenizer.TT_HYPHTERM;
}
// fall through
case 22: break;
case 11:
{ return Tokenizer.TT_BARE_URL;
}
// fall through
case 23: break;
case 12:
{ return Tokenizer.TT_FULL_URL;
}
// fall through
case 24: break;
default:
zzScanError(ZZ_NO_MATCH);
}
}
}
}
}