📄 standardtokenizerimpl.java
字号:
/* The following code was generated by JFlex 1.4.1 on 4/15/08 8:53 AM */package org.apache.lucene.analysis.standard;/** * Licensed to the Apache Software Foundation (ASF) under one or more * contributor license agreements. See the NOTICE file distributed with * this work for additional information regarding copyright ownership. * The ASF licenses this file to You under the Apache License, Version 2.0 * (the "License"); you may not use this file except in compliance with * the License. You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */import org.apache.lucene.analysis.Token;/** * This class is a scanner generated by * <a href="http://www.jflex.de/">JFlex</a> 1.4.1 * on 4/15/08 8:53 AM from the specification file * <tt>/tango/mike/src/lucene.23.clean/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex</tt> */class StandardTokenizerImpl { /** 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; /** * Translates characters to character classes */ private static final String ZZ_CMAP_PACKED = "\11\0\1\0\1\16\1\0\1\0\1\15\22\0\1\0\5\0\1\3"+ "\1\1\4\0\1\7\1\5\1\2\1\7\12\11\6\0\1\4\32\10"+ "\4\0\1\6\1\0\32\10\105\0\27\10\1\0\37\10\1\0\u0568\10"+ "\12\12\206\10\12\12\u026c\10\12\12\166\10\12\12\166\10\12\12\166\10"+ "\12\12\166\10\12\12\167\10\11\12\166\10\12\12\166\10\12\12\166\10"+ "\12\12\340\10\12\12\166\10\12\12\u0166\10\12\12\266\10\u0100\10\u0e00\10"+ "\u1040\0\u0150\14\140\0\20\14\u0100\0\200\14\200\0\u19c0\14\100\0\u5200\14"+ "\u0c00\0\u2bb0\13\u2150\0\u0200\14\u0465\0\73\14\75\10\43\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 = "\1\0\1\1\4\2\1\3\1\1\6\0\2\2\6\0"+ "\1\4\4\5\2\6\2\0\1\7\1\0\1\7\3\5"+ "\6\7\3\5\1\10\1\0\1\11\2\0\1\10\1\11"+ "\1\0\2\11\2\10\2\5\1\12"; private static int [] zzUnpackAction() { int [] result = new int[61]; 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\17\0\36\0\55\0\74\0\113\0\17\0\132"+ "\0\151\0\170\0\207\0\226\0\245\0\264\0\303\0\322"+ "\0\341\0\360\0\377\0\u010e\0\u011d\0\u012c\0\u013b\0\u014a"+ "\0\u0159\0\u0168\0\u0177\0\207\0\u0186\0\u0195\0\u01a4\0\u01b3"+ "\0\u01c2\0\u01d1\0\u01e0\0\u01ef\0\u01fe\0\u020d\0\u021c\0\u022b"+ "\0\u023a\0\u0249\0\u0258\0\u0267\0\u0276\0\u0285\0\u0294\0\u02a3"+ "\0\u02b2\0\u02c1\0\u02d0\0\u02df\0\u02ee\0\u02fd\0\u012c\0\341"+ "\0\170\0\u011d\0\u030c\0\u031b\0\u032a"; private static int [] zzUnpackRowMap() { int [] result = new int[61]; 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 = "\10\2\1\3\1\4\1\5\1\6\1\7\1\10\1\2"+ "\20\0\1\11\1\12\1\13\1\14\2\15\1\16\1\17"+ "\1\4\1\20\1\6\5\0\1\21\1\0\1\22\2\23"+ "\1\24\3\4\1\6\4\0\1\11\1\25\1\13\1\14"+ "\2\23\1\24\1\20\1\4\1\20\1\6\5\0\1\26"+ "\1\0\1\22\2\15\1\16\4\6\21\0\1\2\10\0"+ "\1\27\1\0\1\27\14\0\1\30\1\31\1\32\1\33"+ "\13\0\1\34\1\0\1\34\14\0\1\35\1\36\1\35"+ "\1\36\13\0\1\37\2\40\1\41\13\0\1\16\2\42"+ "\5\0\1\11\1\26\1\13\1\14\2\15\1\16\1\17"+ "\1\4\1\20\1\6\4\0\1\11\1\21\1\13\1\14"+ "\2\23\1\24\1\20\1\4\1\20\1\6\13\0\1\43"+ "\2\44\1\45\13\0\4\36\13\0\1\46\2\47\1\50"+ "\13\0\1\51\2\52\1\53\13\0\1\54\1\44\1\55"+ "\1\45\13\0\1\56\2\31\1\33\4\0\1\11\6\0"+ "\1\27\1\0\1\27\6\0\1\57\1\0\1\22\2\60"+ "\1\0\1\56\2\31\1\33\5\0\1\61\1\0\1\22"+ "\2\62\1\63\3\31\1\33\5\0\1\64\1\0\1\22"+ "\2\62\1\63\3\31\1\33\5\0\1\65\1\0\1\22"+ "\2\60\1\0\4\33\5\0\1\66\2\0\1\66\2\0"+ "\1\35\1\36\1\35\1\36\5\0\1\66\2\0\1\66"+ "\2\0\4\36\5\0\1\60\1\0\1\22\2\60\1\0"+ "\1\37\2\40\1\41\5\0\1\62\1\0\1\22\2\62"+ "\1\63\3\40\1\41\5\0\1\60\1\0\1\22\2\60"+ "\1\0\4\41\5\0\1\63\2\0\3\63\3\42\6\0"+ "\1\67\1\0\1\22\2\15\1\16\1\43\2\44\1\45"+ "\5\0\1\70\1\0\1\22\2\23\1\24\3\44\1\45"+ "\5\0\1\67\1\0\1\22\2\15\1\16\4\45\5\0"+ "\1\15\1\0\1\22\2\15\1\16\1\46\2\47\1\50"+ "\5\0\1\23\1\0\1\22\2\23\1\24\3\47\1\50"+ "\5\0\1\15\1\0\1\22\2\15\1\16\4\50\5\0"+ "\1\16\2\0\3\16\1\51\2\52\1\53\5\0\1\24"+ "\2\0\3\24\3\52\1\53\5\0\1\16\2\0\3\16"+ "\4\53\5\0\1\71\1\0\1\22\2\15\1\16\1\43"+ "\2\44\1\45\5\0\1\72\1\0\1\22\2\23\1\24"+ "\3\44\1\45\5\0\1\65\1\0\1\22\2\60\1\0"+ "\1\56\2\31\1\33\13\0\1\73\1\33\1\73\1\33"+ "\13\0\4\41\13\0\4\45\13\0\4\50\13\0\4\53"+ "\13\0\1\74\1\45\1\74\1\45\13\0\4\33\13\0"+ "\4\75\5\0\1\57\1\0\1\22\2\60\1\0\4\33"+ "\5\0\1\71\1\0\1\22\2\15\1\16\4\45\5\0"+ "\1\66\2\0\1\66\2\0\4\75\3\0"; private static int [] zzUnpackTrans() { int [] result = new int[825]; 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 = "\1\0\1\11\4\1\1\11\1\1\6\0\2\1\6\0"+ "\7\1\2\0\1\1\1\0\16\1\1\0\1\1\2\0"+ "\2\1\1\0\7\1"; private static int [] zzUnpackAttribute() { int [] result = new int[61]; 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[] = new char[ZZ_BUFFERSIZE]; /** the textposition at the last accepting state */ private int zzMarkedPos; /** the textposition at the last state to be included in yytext */ private int zzPushbackPos; /** 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; /** 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; /** * zzAtBOL == true <=> the scanner is currently at the beginning of a line */ private boolean zzAtBOL = true; /** zzAtEOF == true <=> the scanner is at the EOF */ private boolean zzAtEOF; /* user code: */public static final int ALPHANUM = StandardTokenizer.ALPHANUM;public static final int APOSTROPHE = StandardTokenizer.APOSTROPHE;public static final int ACRONYM = StandardTokenizer.ACRONYM;public static final int COMPANY = StandardTokenizer.COMPANY;public static final int EMAIL = StandardTokenizer.EMAIL;public static final int HOST = StandardTokenizer.HOST;public static final int NUM = StandardTokenizer.NUM;public static final int CJ = StandardTokenizer.CJ;/** * @deprecated this solves a bug where HOSTs that end with '.' are identified * as ACRONYMs. It is deprecated and will be removed in the next * release. */public static final int ACRONYM_DEP = StandardTokenizer.ACRONYM_DEP;public static final String [] TOKEN_TYPES = StandardTokenizer.TOKEN_TYPES;public final int yychar(){ return yychar;}/** * Fills Lucene token with the current token text. */final void getText(Token t) { t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);} /** * 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. */ StandardTokenizerImpl(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.
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -