Removes 's from the end of words.
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizer.java
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizer.java (revision 931671)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizer.java (working copy)
@@ -55,7 +55,7 @@
public final class StandardTokenizer extends Tokenizer {
/** A private instance of the JFlex-constructed scanner */
- private final StandardTokenizerImpl scanner;
+ private StandardTokenizerInterface scanner;
public static final int ALPHANUM = 0;
public static final int APOSTROPHE = 1;
@@ -111,7 +111,6 @@
*/
public StandardTokenizer(Version matchVersion, Reader input) {
super();
- this.scanner = new StandardTokenizerImpl(input);
init(input, matchVersion);
}
@@ -120,7 +119,6 @@
*/
public StandardTokenizer(Version matchVersion, AttributeSource source, Reader input) {
super(source);
- this.scanner = new StandardTokenizerImpl(input);
init(input, matchVersion);
}
@@ -129,29 +127,26 @@
*/
public StandardTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
super(factory);
- this.scanner = new StandardTokenizerImpl(input);
init(input, matchVersion);
}
- private void init(Reader input, Version matchVersion) {
+ private final void init(Reader input, Version matchVersion) {
+ this.scanner = matchVersion.onOrAfter(Version.LUCENE_31) ?
+ new StandardTokenizerImpl31(input) : new StandardTokenizerImplOrig(input);
if (matchVersion.onOrAfter(Version.LUCENE_24)) {
replaceInvalidAcronym = true;
} else {
replaceInvalidAcronym = false;
}
this.input = input;
- termAtt = addAttribute(TermAttribute.class);
- offsetAtt = addAttribute(OffsetAttribute.class);
- posIncrAtt = addAttribute(PositionIncrementAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
}
// this tokenizer generates three attributes:
- // offset, positionIncrement and type
- private TermAttribute termAtt;
- private OffsetAttribute offsetAtt;
- private PositionIncrementAttribute posIncrAtt;
- private TypeAttribute typeAtt;
+ // term offset, positionIncrement and type
+ private final TermAttribute termAtt = addAttribute(TermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
/*
* (non-Javadoc)
@@ -166,7 +161,7 @@
while(true) {
int tokenType = scanner.getNextToken();
- if (tokenType == StandardTokenizerImpl.YYEOF) {
+ if (tokenType == StandardTokenizerInterface.YYEOF) {
return false;
}
@@ -178,15 +173,15 @@
// This 'if' should be removed in the next release. For now, it converts
// invalid acronyms to HOST. When removed, only the 'else' part should
// remain.
- if (tokenType == StandardTokenizerImpl.ACRONYM_DEP) {
+ if (tokenType == StandardTokenizer.ACRONYM_DEP) {
if (replaceInvalidAcronym) {
- typeAtt.setType(StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.HOST]);
+ typeAtt.setType(StandardTokenizer.TOKEN_TYPES[StandardTokenizer.HOST]);
termAtt.setTermLength(termAtt.termLength() - 1); // remove extra '.'
} else {
- typeAtt.setType(StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.ACRONYM]);
+ typeAtt.setType(StandardTokenizer.TOKEN_TYPES[StandardTokenizer.ACRONYM]);
}
} else {
- typeAtt.setType(StandardTokenizerImpl.TOKEN_TYPES[tokenType]);
+ typeAtt.setType(StandardTokenizer.TOKEN_TYPES[tokenType]);
}
return true;
} else
@@ -211,7 +206,7 @@
@Override
public void reset() throws IOException {
super.reset();
- scanner.yyreset(input);
+ scanner.reset(input);
}
@Override
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java (revision 931671)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.java (working copy)
@@ -1,724 +0,0 @@
-/* The following code was generated by JFlex 1.4.1 on 9/4/08 6:49 PM */
-
-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.
- */
-
-/*
-
-WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
- the tokenizer, only use Java 1.4 !!!
- This grammar currently uses constructs (eg :digit:, :letter:) whose
- meaning can vary according to the JRE used to run jflex. See
- https://issues.apache.org/jira/browse/LUCENE-1126 for details.
- For current backwards compatibility it is needed to support
- only Java 1.4 - this will change in Lucene 3.1.
-
-*/
-
-import org.apache.lucene.analysis.Token;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
-
-
-/**
- * This class is a scanner generated by
- * JFlex 1.4.1
- * on 9/4/08 6:49 PM from the specification file
- * /tango/mike/src/lucene.standarddigit/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
- */
-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\15\1\0\1\0\1\14\22\0\1\0\5\0\1\5"+
- "\1\3\4\0\1\11\1\7\1\4\1\11\12\2\6\0\1\6\32\12"+
- "\4\0\1\10\1\0\32\12\57\0\1\12\12\0\1\12\4\0\1\12"+
- "\5\0\27\12\1\0\37\12\1\0\u0128\12\2\0\22\12\34\0\136\12"+
- "\2\0\11\12\2\0\7\12\16\0\2\12\16\0\5\12\11\0\1\12"+
- "\213\0\1\12\13\0\1\12\1\0\3\12\1\0\1\12\1\0\24\12"+
- "\1\0\54\12\1\0\10\12\2\0\32\12\14\0\202\12\12\0\71\12"+
- "\2\0\2\12\2\0\2\12\3\0\46\12\2\0\2\12\67\0\46\12"+
- "\2\0\1\12\7\0\47\12\110\0\33\12\5\0\3\12\56\0\32\12"+
- "\5\0\13\12\25\0\12\2\7\0\143\12\1\0\1\12\17\0\2\12"+
- "\11\0\12\2\3\12\23\0\1\12\1\0\33\12\123\0\46\12\u015f\0"+
- "\65\12\3\0\1\12\22\0\1\12\7\0\12\12\4\0\12\2\25\0"+
- "\10\12\2\0\2\12\2\0\26\12\1\0\7\12\1\0\1\12\3\0"+
- "\4\12\42\0\2\12\1\0\3\12\4\0\12\2\2\12\23\0\6\12"+
- "\4\0\2\12\2\0\26\12\1\0\7\12\1\0\2\12\1\0\2\12"+
- "\1\0\2\12\37\0\4\12\1\0\1\12\7\0\12\2\2\0\3\12"+
- "\20\0\7\12\1\0\1\12\1\0\3\12\1\0\26\12\1\0\7\12"+
- "\1\0\2\12\1\0\5\12\3\0\1\12\22\0\1\12\17\0\1\12"+
- "\5\0\12\2\25\0\10\12\2\0\2\12\2\0\26\12\1\0\7\12"+
- "\1\0\2\12\2\0\4\12\3\0\1\12\36\0\2\12\1\0\3\12"+
- "\4\0\12\2\25\0\6\12\3\0\3\12\1\0\4\12\3\0\2\12"+
- "\1\0\1\12\1\0\2\12\3\0\2\12\3\0\3\12\3\0\10\12"+
- "\1\0\3\12\55\0\11\2\25\0\10\12\1\0\3\12\1\0\27\12"+
- "\1\0\12\12\1\0\5\12\46\0\2\12\4\0\12\2\25\0\10\12"+
- "\1\0\3\12\1\0\27\12\1\0\12\12\1\0\5\12\44\0\1\12"+
- "\1\0\2\12\4\0\12\2\25\0\10\12\1\0\3\12\1\0\27\12"+
- "\1\0\20\12\46\0\2\12\4\0\12\2\25\0\22\12\3\0\30\12"+
- "\1\0\11\12\1\0\1\12\2\0\7\12\71\0\1\1\60\12\1\1"+
- "\2\12\14\1\7\12\11\1\12\2\47\0\2\12\1\0\1\12\2\0"+
- "\2\12\1\0\1\12\2\0\1\12\6\0\4\12\1\0\7\12\1\0"+
- "\3\12\1\0\1\12\1\0\1\12\2\0\2\12\1\0\4\12\1\0"+
- "\2\12\11\0\1\12\2\0\5\12\1\0\1\12\11\0\12\2\2\0"+
- "\2\12\42\0\1\12\37\0\12\2\26\0\10\12\1\0\42\12\35\0"+
- "\4\12\164\0\42\12\1\0\5\12\1\0\2\12\25\0\12\2\6\0"+
- "\6\12\112\0\46\12\12\0\47\12\11\0\132\12\5\0\104\12\5\0"+
- "\122\12\6\0\7\12\1\0\77\12\1\0\1\12\1\0\4\12\2\0"+
- "\7\12\1\0\1\12\1\0\4\12\2\0\47\12\1\0\1\12\1\0"+
- "\4\12\2\0\37\12\1\0\1\12\1\0\4\12\2\0\7\12\1\0"+
- "\1\12\1\0\4\12\2\0\7\12\1\0\7\12\1\0\27\12\1\0"+
- "\37\12\1\0\1\12\1\0\4\12\2\0\7\12\1\0\47\12\1\0"+
- "\23\12\16\0\11\2\56\0\125\12\14\0\u026c\12\2\0\10\12\12\0"+
- "\32\12\5\0\113\12\225\0\64\12\54\0\12\2\46\0\12\2\6\0"+
- "\130\12\10\0\51\12\u0557\0\234\12\4\0\132\12\6\0\26\12\2\0"+
- "\6\12\2\0\46\12\2\0\6\12\2\0\10\12\1\0\1\12\1\0"+
- "\1\12\1\0\1\12\1\0\37\12\2\0\65\12\1\0\7\12\1\0"+
- "\1\12\3\0\3\12\1\0\7\12\3\0\4\12\2\0\6\12\4\0"+
- "\15\12\5\0\3\12\1\0\7\12\202\0\1\12\202\0\1\12\4\0"+
- "\1\12\2\0\12\12\1\0\1\12\3\0\5\12\6\0\1\12\1\0"+
- "\1\12\1\0\1\12\1\0\4\12\1\0\3\12\1\0\7\12\u0ecb\0"+
- "\2\12\52\0\5\12\12\0\1\13\124\13\10\13\2\13\2\13\132\13"+
- "\1\13\3\13\6\13\50\13\3\13\1\0\136\12\21\0\30\12\70\0"+
- "\20\13\u0100\0\200\13\200\0\u19b6\13\12\13\100\0\u51a6\13\132\13\u048d\12"+
- "\u0773\0\u2ba4\12\u215c\0\u012e\13\322\13\7\12\14\0\5\12\5\0\1\12"+
- "\1\0\12\12\1\0\15\12\1\0\5\12\1\0\1\12\1\0\2\12"+
- "\1\0\2\12\1\0\154\12\41\0\u016b\12\22\0\100\12\2\0\66\12"+
- "\50\0\14\12\164\0\3\12\1\0\1\12\1\0\207\12\23\0\12\2"+
- "\7\0\32\12\6\0\32\12\12\0\1\13\72\13\37\12\3\0\6\12"+
- "\2\0\6\12\2\0\6\12\2\0\3\12\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\3\2\1\3\1\1\13\0\1\2\3\4"+
- "\2\0\1\5\1\0\1\5\3\4\6\5\1\6\1\4"+
- "\2\7\1\10\1\0\1\10\3\0\2\10\1\11\1\12"+
- "\1\4";
-
- private static int [] zzUnpackAction() {
- int [] result = new int[51];
- 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\16\0\34\0\52\0\70\0\16\0\106\0\124"+
- "\0\142\0\160\0\176\0\214\0\232\0\250\0\266\0\304"+
- "\0\322\0\340\0\356\0\374\0\u010a\0\u0118\0\u0126\0\u0134"+
- "\0\u0142\0\u0150\0\u015e\0\u016c\0\u017a\0\u0188\0\u0196\0\u01a4"+
- "\0\u01b2\0\u01c0\0\u01ce\0\u01dc\0\u01ea\0\u01f8\0\322\0\u0206"+
- "\0\u0214\0\u0222\0\u0230\0\u023e\0\u024c\0\u025a\0\124\0\214"+
- "\0\u0268\0\u0276\0\u0284";
-
- private static int [] zzUnpackRowMap() {
- int [] result = new int[51];
- 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 =
- "\1\2\1\3\1\4\7\2\1\5\1\6\1\7\1\2"+
- "\17\0\2\3\1\0\1\10\1\0\1\11\2\12\1\13"+
- "\1\3\4\0\1\3\1\4\1\0\1\14\1\0\1\11"+
- "\2\15\1\16\1\4\4\0\1\3\1\4\1\17\1\20"+
- "\1\21\1\22\2\12\1\13\1\23\20\0\1\2\1\0"+
- "\1\24\1\25\7\0\1\26\4\0\2\27\7\0\1\27"+
- "\4\0\1\30\1\31\7\0\1\32\5\0\1\33\7\0"+
- "\1\13\4\0\1\34\1\35\7\0\1\36\4\0\1\37"+
- "\1\40\7\0\1\41\4\0\1\42\1\43\7\0\1\44"+
- "\15\0\1\45\4\0\1\24\1\25\7\0\1\46\15\0"+
- "\1\47\4\0\2\27\7\0\1\50\4\0\1\3\1\4"+
- "\1\17\1\10\1\21\1\22\2\12\1\13\1\23\4\0"+
- "\2\24\1\0\1\51\1\0\1\11\2\52\1\0\1\24"+
- "\4\0\1\24\1\25\1\0\1\53\1\0\1\11\2\54"+
- "\1\55\1\25\4\0\1\24\1\25\1\0\1\51\1\0"+
- "\1\11\2\52\1\0\1\26\4\0\2\27\1\0\1\56"+
- "\2\0\1\56\2\0\1\27\4\0\2\30\1\0\1\52"+
- "\1\0\1\11\2\52\1\0\1\30\4\0\1\30\1\31"+
- "\1\0\1\54\1\0\1\11\2\54\1\55\1\31\4\0"+
- "\1\30\1\31\1\0\1\52\1\0\1\11\2\52\1\0"+
- "\1\32\5\0\1\33\1\0\1\55\2\0\3\55\1\33"+
- "\4\0\2\34\1\0\1\57\1\0\1\11\2\12\1\13"+
- "\1\34\4\0\1\34\1\35\1\0\1\60\1\0\1\11"+
- "\2\15\1\16\1\35\4\0\1\34\1\35\1\0\1\57"+
- "\1\0\1\11\2\12\1\13\1\36\4\0\2\37\1\0"+
- "\1\12\1\0\1\11\2\12\1\13\1\37\4\0\1\37"+
- "\1\40\1\0\1\15\1\0\1\11\2\15\1\16\1\40"+
- "\4\0\1\37\1\40\1\0\1\12\1\0\1\11\2\12"+
- "\1\13\1\41\4\0\2\42\1\0\1\13\2\0\3\13"+
- "\1\42\4\0\1\42\1\43\1\0\1\16\2\0\3\16"+
- "\1\43\4\0\1\42\1\43\1\0\1\13\2\0\3\13"+
- "\1\44\6\0\1\17\6\0\1\45\4\0\1\24\1\25"+
- "\1\0\1\61\1\0\1\11\2\52\1\0\1\26\4\0"+
- "\2\27\1\0\1\56\2\0\1\56\2\0\1\50\4\0"+
- "\2\24\7\0\1\24\4\0\2\30\7\0\1\30\4\0"+
- "\2\34\7\0\1\34\4\0\2\37\7\0\1\37\4\0"+
- "\2\42\7\0\1\42\4\0\2\62\7\0\1\62\4\0"+
- "\2\24\7\0\1\63\4\0\2\62\1\0\1\56\2\0"+
- "\1\56\2\0\1\62\4\0\2\24\1\0\1\61\1\0"+
- "\1\11\2\52\1\0\1\24\3\0";
-
- private static int [] zzUnpackTrans() {
- int [] result = new int[658];
- 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 aState
- */
- private static final int [] ZZ_ATTRIBUTE = zzUnpackAttribute();
-
- private static final String ZZ_ATTRIBUTE_PACKED_0 =
- "\1\0\1\11\3\1\1\11\1\1\13\0\4\1\2\0"+
- "\1\1\1\0\17\1\1\0\1\1\3\0\5\1";
-
- private static int [] zzUnpackAttribute() {
- int [] result = new int[51];
- 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.
- */
-@Deprecated
-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);
-}
-
-/**
- * Fills TermAttribute with the current token text.
- */
-final void getText(TermAttribute 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.
- */
- StandardTokenizerImpl(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 < 1154) {
- int count = packed.charAt(i++);
- char value = packed.charAt(i++);
- do map[j++] = value; while (--count > 0);
- }
- return map;
- }
-
-
- /**
- * Refills the input buffer.
- *
- * @return 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) {
- System.arraycopy(zzBuffer, zzStartRead,
- zzBuffer, 0,
- zzEndRead-zzStartRead);
-
- /* translate stored positions */
- zzEndRead-= zzStartRead;
- zzCurrentPos-= zzStartRead;
- zzMarkedPos-= zzStartRead;
- zzPushbackPos-= zzStartRead;
- zzStartRead = 0;
- }
-
- /* is the buffer big enough? */
- if (zzCurrentPos >= zzBuffer.length) {
- /* if not: blow it up */
- char newBuffer[] = new char[zzCurrentPos*2];
- System.arraycopy(zzBuffer, 0, newBuffer, 0, zzBuffer.length);
- zzBuffer = newBuffer;
- }
-
- /* finally: fill the buffer with new input */
- int numRead = zzReader.read(zzBuffer, zzEndRead,
- zzBuffer.length-zzEndRead);
-
- if (numRead < 0) {
- return true;
- }
- else {
- zzEndRead+= numRead;
- return false;
- }
- }
-
-
- /**
- * 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();
- }
-
-
- /**
- * 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 ZZ_INITIAL.
- *
- * @param reader the new input stream
- */
- public final void yyreset(java.io.Reader reader) {
- zzReader = reader;
- zzAtBOL = true;
- zzAtEOF = false;
- zzEndRead = zzStartRead = 0;
- zzCurrentPos = zzMarkedPos = zzPushbackPos = 0;
- yyline = yychar = yycolumn = 0;
- zzLexicalState = YYINITIAL;
- }
-
-
- /**
- * 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 pos 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 int getNextToken() 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;
-
- yychar+= zzMarkedPosL-zzStartRead;
-
- 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 4:
- { return HOST;
- }
- case 11: break;
- case 9:
- { return ACRONYM;
- }
- case 12: break;
- case 8:
- { return ACRONYM_DEP;
- }
- case 13: break;
- case 1:
- { /* ignore */
- }
- case 14: break;
- case 5:
- { return NUM;
- }
- case 15: break;
- case 3:
- { return CJ;
- }
- case 16: break;
- case 2:
- { return ALPHANUM;
- }
- case 17: break;
- case 7:
- { return COMPANY;
- }
- case 18: break;
- case 6:
- { return APOSTROPHE;
- }
- case 19: break;
- case 10:
- { return EMAIL;
- }
- case 20: break;
- default:
- if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
- zzAtEOF = true;
- return YYEOF;
- }
- else {
- zzScanError(ZZ_NO_MATCH);
- }
- }
- }
- }
-
-
-}
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex (revision 931671)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex (working copy)
@@ -1,146 +0,0 @@
-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.
- */
-
-/*
-
-WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
- the tokenizer, only use Java 1.4 !!!
- This grammar currently uses constructs (eg :digit:, :letter:) whose
- meaning can vary according to the JRE used to run jflex. See
- https://issues.apache.org/jira/browse/LUCENE-1126 for details.
- For current backwards compatibility it is needed to support
- only Java 1.4 - this will change in Lucene 3.1.
-
-*/
-
-import org.apache.lucene.analysis.Token;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
-
-%%
-
-%class StandardTokenizerImpl
-%unicode
-%integer
-%function getNextToken
-%pack
-%char
-
-%{
-
-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.
- */
-@Deprecated
-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);
-}
-
-/**
- * Fills TermAttribute with the current token text.
- */
-final void getText(TermAttribute t) {
- t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
-}
-
-%}
-
-THAI = [\u0E00-\u0E59]
-
-// basic word: a sequence of digits & letters (includes Thai to enable ThaiAnalyzer to function)
-ALPHANUM = ({LETTER}|{THAI}|[:digit:])+
-
-// internal apostrophes: O'Reilly, you're, O'Reilly's
-// use a post-filter to remove possessives
-APOSTROPHE = {ALPHA} ("'" {ALPHA})+
-
-// acronyms: U.S.A., I.B.M., etc.
-// use a post-filter to remove dots
-ACRONYM = {LETTER} "." ({LETTER} ".")+
-
-ACRONYM_DEP = {ALPHANUM} "." ({ALPHANUM} ".")+
-
-// company names like AT&T and Excite@Home.
-COMPANY = {ALPHA} ("&"|"@") {ALPHA}
-
-// email addresses
-EMAIL = {ALPHANUM} (("."|"-"|"_") {ALPHANUM})* "@" {ALPHANUM} (("."|"-") {ALPHANUM})+
-
-// hostname
-HOST = {ALPHANUM} ((".") {ALPHANUM})+
-
-// floating point, serial, model numbers, ip addresses, etc.
-// every other segment must have at least one digit
-NUM = ({ALPHANUM} {P} {HAS_DIGIT}
- | {HAS_DIGIT} {P} {ALPHANUM}
- | {ALPHANUM} ({P} {HAS_DIGIT} {P} {ALPHANUM})+
- | {HAS_DIGIT} ({P} {ALPHANUM} {P} {HAS_DIGIT})+
- | {ALPHANUM} {P} {HAS_DIGIT} ({P} {ALPHANUM} {P} {HAS_DIGIT})+
- | {HAS_DIGIT} {P} {ALPHANUM} ({P} {HAS_DIGIT} {P} {ALPHANUM})+)
-
-// punctuation
-P = ("_"|"-"|"/"|"."|",")
-
-// at least one digit
-HAS_DIGIT = ({LETTER}|[:digit:])* [:digit:] ({LETTER}|[:digit:])*
-
-ALPHA = ({LETTER})+
-
-// From the JFlex manual: "the expression that matches everything of not matched by is !(!|)"
-LETTER = !(![:letter:]|{CJ})
-
-// Chinese and Japanese (but NOT Korean, which is included in [:letter:])
-CJ = [\u3100-\u312f\u3040-\u309F\u30A0-\u30FF\u31F0-\u31FF\u3300-\u337f\u3400-\u4dbf\u4e00-\u9fff\uf900-\ufaff\uff65-\uff9f]
-
-WHITESPACE = \r\n | [ \r\n\t\f]
-
-%%
-
-{ALPHANUM} { return ALPHANUM; }
-{APOSTROPHE} { return APOSTROPHE; }
-{ACRONYM} { return ACRONYM; }
-{COMPANY} { return COMPANY; }
-{EMAIL} { return EMAIL; }
-{HOST} { return HOST; }
-{NUM} { return NUM; }
-{CJ} { return CJ; }
-{ACRONYM_DEP} { return ACRONYM_DEP; }
-
-/** Ignore the rest */
-. | {WHITESPACE} { /* ignore */ }
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.java
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.java (revision 886325)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.java (working copy)
@@ -1,4 +1,4 @@
-/* The following code was generated by JFlex 1.4.1 on 9/4/08 6:49 PM */
+/* The following code was generated by JFlex 1.5.0-SNAPSHOT on 08.04.10 13:01 */
package org.apache.lucene.analysis.standard;
@@ -21,27 +21,22 @@
/*
-WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
- the tokenizer, only use Java 1.4 !!!
- This grammar currently uses constructs (eg :digit:, :letter:) whose
- meaning can vary according to the JRE used to run jflex. See
- https://issues.apache.org/jira/browse/LUCENE-1126 for details.
- For current backwards compatibility it is needed to support
- only Java 1.4 - this will change in Lucene 3.1.
+WARNING: if you change StandardTokenizerImpl*.jflex and need to regenerate
+ the tokenizer, only use the trunk version of JFlex 1.5 at the moment!
*/
-import org.apache.lucene.analysis.Token;
+import java.io.Reader;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
/**
* This class is a scanner generated by
- * JFlex 1.4.1
- * on 9/4/08 6:49 PM from the specification file
- * /tango/mike/src/lucene.standarddigit/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
+ * JFlex 1.5.0-SNAPSHOT
+ * on 08.04.10 13:01 from the specification file
+ * C:/Users/Uwe Schindler/Projects/lucene/trunk-full1/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.jflex
*/
-class StandardTokenizerImpl {
+class StandardTokenizerImpl31 implements StandardTokenizerInterface {
/** This character denotes the end of file */
public static final int YYEOF = -1;
@@ -52,6 +47,16 @@
/** 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
+ };
+
/**
* Translates characters to character classes
*/
@@ -59,59 +64,63 @@
"\11\0\1\0\1\15\1\0\1\0\1\14\22\0\1\0\5\0\1\5"+
"\1\3\4\0\1\11\1\7\1\4\1\11\12\2\6\0\1\6\32\12"+
"\4\0\1\10\1\0\32\12\57\0\1\12\12\0\1\12\4\0\1\12"+
- "\5\0\27\12\1\0\37\12\1\0\u0128\12\2\0\22\12\34\0\136\12"+
- "\2\0\11\12\2\0\7\12\16\0\2\12\16\0\5\12\11\0\1\12"+
- "\213\0\1\12\13\0\1\12\1\0\3\12\1\0\1\12\1\0\24\12"+
- "\1\0\54\12\1\0\10\12\2\0\32\12\14\0\202\12\12\0\71\12"+
- "\2\0\2\12\2\0\2\12\3\0\46\12\2\0\2\12\67\0\46\12"+
- "\2\0\1\12\7\0\47\12\110\0\33\12\5\0\3\12\56\0\32\12"+
- "\5\0\13\12\25\0\12\2\7\0\143\12\1\0\1\12\17\0\2\12"+
- "\11\0\12\2\3\12\23\0\1\12\1\0\33\12\123\0\46\12\u015f\0"+
- "\65\12\3\0\1\12\22\0\1\12\7\0\12\12\4\0\12\2\25\0"+
- "\10\12\2\0\2\12\2\0\26\12\1\0\7\12\1\0\1\12\3\0"+
- "\4\12\42\0\2\12\1\0\3\12\4\0\12\2\2\12\23\0\6\12"+
- "\4\0\2\12\2\0\26\12\1\0\7\12\1\0\2\12\1\0\2\12"+
- "\1\0\2\12\37\0\4\12\1\0\1\12\7\0\12\2\2\0\3\12"+
- "\20\0\7\12\1\0\1\12\1\0\3\12\1\0\26\12\1\0\7\12"+
- "\1\0\2\12\1\0\5\12\3\0\1\12\22\0\1\12\17\0\1\12"+
- "\5\0\12\2\25\0\10\12\2\0\2\12\2\0\26\12\1\0\7\12"+
- "\1\0\2\12\2\0\4\12\3\0\1\12\36\0\2\12\1\0\3\12"+
- "\4\0\12\2\25\0\6\12\3\0\3\12\1\0\4\12\3\0\2\12"+
- "\1\0\1\12\1\0\2\12\3\0\2\12\3\0\3\12\3\0\10\12"+
- "\1\0\3\12\55\0\11\2\25\0\10\12\1\0\3\12\1\0\27\12"+
- "\1\0\12\12\1\0\5\12\46\0\2\12\4\0\12\2\25\0\10\12"+
- "\1\0\3\12\1\0\27\12\1\0\12\12\1\0\5\12\44\0\1\12"+
- "\1\0\2\12\4\0\12\2\25\0\10\12\1\0\3\12\1\0\27\12"+
- "\1\0\20\12\46\0\2\12\4\0\12\2\25\0\22\12\3\0\30\12"+
- "\1\0\11\12\1\0\1\12\2\0\7\12\71\0\1\1\60\12\1\1"+
- "\2\12\14\1\7\12\11\1\12\2\47\0\2\12\1\0\1\12\2\0"+
- "\2\12\1\0\1\12\2\0\1\12\6\0\4\12\1\0\7\12\1\0"+
- "\3\12\1\0\1\12\1\0\1\12\2\0\2\12\1\0\4\12\1\0"+
- "\2\12\11\0\1\12\2\0\5\12\1\0\1\12\11\0\12\2\2\0"+
- "\2\12\42\0\1\12\37\0\12\2\26\0\10\12\1\0\42\12\35\0"+
- "\4\12\164\0\42\12\1\0\5\12\1\0\2\12\25\0\12\2\6\0"+
- "\6\12\112\0\46\12\12\0\47\12\11\0\132\12\5\0\104\12\5\0"+
- "\122\12\6\0\7\12\1\0\77\12\1\0\1\12\1\0\4\12\2\0"+
- "\7\12\1\0\1\12\1\0\4\12\2\0\47\12\1\0\1\12\1\0"+
- "\4\12\2\0\37\12\1\0\1\12\1\0\4\12\2\0\7\12\1\0"+
- "\1\12\1\0\4\12\2\0\7\12\1\0\7\12\1\0\27\12\1\0"+
- "\37\12\1\0\1\12\1\0\4\12\2\0\7\12\1\0\47\12\1\0"+
- "\23\12\16\0\11\2\56\0\125\12\14\0\u026c\12\2\0\10\12\12\0"+
- "\32\12\5\0\113\12\225\0\64\12\54\0\12\2\46\0\12\2\6\0"+
- "\130\12\10\0\51\12\u0557\0\234\12\4\0\132\12\6\0\26\12\2\0"+
- "\6\12\2\0\46\12\2\0\6\12\2\0\10\12\1\0\1\12\1\0"+
- "\1\12\1\0\1\12\1\0\37\12\2\0\65\12\1\0\7\12\1\0"+
- "\1\12\3\0\3\12\1\0\7\12\3\0\4\12\2\0\6\12\4\0"+
- "\15\12\5\0\3\12\1\0\7\12\202\0\1\12\202\0\1\12\4\0"+
- "\1\12\2\0\12\12\1\0\1\12\3\0\5\12\6\0\1\12\1\0"+
- "\1\12\1\0\1\12\1\0\4\12\1\0\3\12\1\0\7\12\u0ecb\0"+
- "\2\12\52\0\5\12\12\0\1\13\124\13\10\13\2\13\2\13\132\13"+
- "\1\13\3\13\6\13\50\13\3\13\1\0\136\12\21\0\30\12\70\0"+
+ "\5\0\27\12\1\0\37\12\1\0\u013f\12\31\0\162\12\4\0\14\12"+
+ "\16\0\5\12\11\0\1\12\213\0\1\12\13\0\1\12\1\0\3\12"+
+ "\1\0\1\12\1\0\24\12\1\0\54\12\1\0\46\12\1\0\5\12"+
+ "\4\0\202\12\10\0\105\12\1\0\46\12\2\0\2\12\6\0\20\12"+
+ "\41\0\46\12\2\0\1\12\7\0\47\12\110\0\33\12\5\0\3\12"+
+ "\56\0\32\12\5\0\13\12\25\0\12\2\4\0\2\12\1\0\143\12"+
+ "\1\0\1\12\17\0\2\12\7\0\2\12\12\2\3\12\2\0\1\12"+
+ "\20\0\1\12\1\0\36\12\35\0\3\12\60\0\46\12\13\0\1\12"+
+ "\u0152\0\66\12\3\0\1\12\22\0\1\12\7\0\12\12\4\0\12\2"+
+ "\25\0\10\12\2\0\2\12\2\0\26\12\1\0\7\12\1\0\1\12"+
+ "\3\0\4\12\3\0\1\12\36\0\2\12\1\0\3\12\4\0\12\2"+
+ "\2\12\23\0\6\12\4\0\2\12\2\0\26\12\1\0\7\12\1\0"+
+ "\2\12\1\0\2\12\1\0\2\12\37\0\4\12\1\0\1\12\7\0"+
+ "\12\2\2\0\3\12\20\0\11\12\1\0\3\12\1\0\26\12\1\0"+
+ "\7\12\1\0\2\12\1\0\5\12\3\0\1\12\22\0\1\12\17\0"+
+ "\2\12\4\0\12\2\25\0\10\12\2\0\2\12\2\0\26\12\1\0"+
+ "\7\12\1\0\2\12\1\0\5\12\3\0\1\12\36\0\2\12\1\0"+
+ "\3\12\4\0\12\2\1\0\1\12\21\0\1\12\1\0\6\12\3\0"+
+ "\3\12\1\0\4\12\3\0\2\12\1\0\1\12\1\0\2\12\3\0"+
+ "\2\12\3\0\3\12\3\0\10\12\1\0\3\12\55\0\11\2\25\0"+
+ "\10\12\1\0\3\12\1\0\27\12\1\0\12\12\1\0\5\12\46\0"+
+ "\2\12\4\0\12\2\25\0\10\12\1\0\3\12\1\0\27\12\1\0"+
+ "\12\12\1\0\5\12\3\0\1\12\40\0\1\12\1\0\2\12\4\0"+
+ "\12\2\25\0\10\12\1\0\3\12\1\0\27\12\1\0\20\12\46\0"+
+ "\2\12\4\0\12\2\25\0\22\12\3\0\30\12\1\0\11\12\1\0"+
+ "\1\12\2\0\7\12\71\0\1\1\60\12\1\1\2\12\14\1\7\12"+
+ "\11\1\12\2\47\0\2\12\1\0\1\12\2\0\2\12\1\0\1\12"+
+ "\2\0\1\12\6\0\4\12\1\0\7\12\1\0\3\12\1\0\1\12"+
+ "\1\0\1\12\2\0\2\12\1\0\4\12\1\0\2\12\11\0\1\12"+
+ "\2\0\5\12\1\0\1\12\11\0\12\2\2\0\2\12\42\0\1\12"+
+ "\37\0\12\2\26\0\10\12\1\0\42\12\35\0\4\12\164\0\42\12"+
+ "\1\0\5\12\1\0\2\12\25\0\12\2\6\0\6\12\112\0\46\12"+
+ "\12\0\51\12\7\0\132\12\5\0\104\12\5\0\122\12\6\0\7\12"+
+ "\1\0\77\12\1\0\1\12\1\0\4\12\2\0\7\12\1\0\1\12"+
+ "\1\0\4\12\2\0\47\12\1\0\1\12\1\0\4\12\2\0\37\12"+
+ "\1\0\1\12\1\0\4\12\2\0\7\12\1\0\1\12\1\0\4\12"+
+ "\2\0\7\12\1\0\7\12\1\0\27\12\1\0\37\12\1\0\1\12"+
+ "\1\0\4\12\2\0\7\12\1\0\47\12\1\0\23\12\16\0\11\2"+
+ "\56\0\125\12\14\0\u026c\12\2\0\10\12\12\0\32\12\5\0\113\12"+
+ "\25\0\15\12\1\0\4\12\16\0\22\12\16\0\22\12\16\0\15\12"+
+ "\1\0\3\12\17\0\64\12\43\0\1\12\4\0\1\12\3\0\12\2"+
+ "\46\0\12\2\6\0\130\12\10\0\51\12\127\0\35\12\51\0\12\2"+
+ "\36\12\2\0\5\12\u038b\0\154\12\224\0\234\12\4\0\132\12\6\0"+
+ "\26\12\2\0\6\12\2\0\46\12\2\0\6\12\2\0\10\12\1\0"+
+ "\1\12\1\0\1\12\1\0\1\12\1\0\37\12\2\0\65\12\1\0"+
+ "\7\12\1\0\1\12\3\0\3\12\1\0\7\12\3\0\4\12\2\0"+
+ "\6\12\4\0\15\12\5\0\3\12\1\0\7\12\164\0\1\12\15\0"+
+ "\1\12\202\0\1\12\4\0\1\12\2\0\12\12\1\0\1\12\3\0"+
+ "\5\12\6\0\1\12\1\0\1\12\1\0\1\12\1\0\4\12\1\0"+
+ "\3\12\1\0\7\12\3\0\3\12\5\0\5\12\u0ebb\0\2\12\52\0"+
+ "\5\12\5\0\2\12\3\0\1\13\126\13\6\13\3\13\1\13\132\13"+
+ "\1\13\4\13\5\13\50\13\3\13\1\0\136\12\21\0\30\12\70\0"+
"\20\13\u0100\0\200\13\200\0\u19b6\13\12\13\100\0\u51a6\13\132\13\u048d\12"+
- "\u0773\0\u2ba4\12\u215c\0\u012e\13\322\13\7\12\14\0\5\12\5\0\1\12"+
- "\1\0\12\12\1\0\15\12\1\0\5\12\1\0\1\12\1\0\2\12"+
- "\1\0\2\12\1\0\154\12\41\0\u016b\12\22\0\100\12\2\0\66\12"+
- "\50\0\14\12\164\0\3\12\1\0\1\12\1\0\207\12\23\0\12\2"+
+ "\u0773\0\u2ba4\12\u215c\0\u012e\13\2\13\73\13\225\13\7\12\14\0\5\12"+
+ "\5\0\1\12\1\0\12\12\1\0\15\12\1\0\5\12\1\0\1\12"+
+ "\1\0\2\12\1\0\2\12\1\0\154\12\41\0\u016b\12\22\0\100\12"+
+ "\2\0\66\12\50\0\14\12\164\0\5\12\1\0\207\12\23\0\12\2"+
"\7\0\32\12\6\0\32\12\12\0\1\13\72\13\37\12\3\0\6\12"+
"\2\0\6\12\2\0\6\12\2\0\3\12\43\0";
@@ -307,9 +316,6 @@
/** 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;
@@ -340,6 +346,9 @@
/** zzAtEOF == true <=> the scanner is at the EOF */
private boolean zzAtEOF;
+ /** denotes if the user-EOF-code has already been executed */
+ private boolean zzEOFDone;
+
/* user code: */
public static final int ALPHANUM = StandardTokenizer.ALPHANUM;
@@ -364,27 +373,32 @@
}
/**
- * Fills Lucene token with the current token text.
+ * Fills TermAttribute with the current token text.
*/
-final void getText(Token t) {
+public final void getText(TermAttribute t) {
t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}
/**
- * Fills TermAttribute with the current token text.
+ * Resets the Tokenizer to a new Reader.
*/
-final void getText(TermAttribute t) {
- t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
+public final void reset(Reader r) {
+ // reset to default buffer size, if buffer has grown
+ if (zzBuffer.length > ZZ_BUFFERSIZE) {
+ zzBuffer = new char[ZZ_BUFFERSIZE];
+ }
+ yyreset(r);
}
+
/**
* 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) {
+ StandardTokenizerImpl31(java.io.Reader in) {
this.zzReader = in;
}
@@ -394,7 +408,7 @@
*
* @param in the java.io.Inputstream to read input from.
*/
- StandardTokenizerImpl(java.io.InputStream in) {
+ StandardTokenizerImpl31(java.io.InputStream in) {
this(new java.io.InputStreamReader(in));
}
@@ -408,7 +422,7 @@
char [] map = new char[0x10000];
int i = 0; /* index in packed string */
int j = 0; /* index in unpacked array */
- while (i < 1154) {
+ while (i < 1234) {
int count = packed.charAt(i++);
char value = packed.charAt(i++);
do map[j++] = value; while (--count > 0);
@@ -436,7 +450,6 @@
zzEndRead-= zzStartRead;
zzCurrentPos-= zzStartRead;
zzMarkedPos-= zzStartRead;
- zzPushbackPos-= zzStartRead;
zzStartRead = 0;
}
@@ -452,13 +465,23 @@
int numRead = zzReader.read(zzBuffer, zzEndRead,
zzBuffer.length-zzEndRead);
- if (numRead < 0) {
- return true;
- }
- else {
+ if (numRead > 0) {
zzEndRead+= numRead;
return false;
}
+ // unlikely but not impossible: read 0 characters, but not at end of stream
+ if (numRead == 0) {
+ int c = zzReader.read();
+ if (c == -1) {
+ return true;
+ } else {
+ zzBuffer[zzEndRead++] = (char) c;
+ return false;
+ }
+ }
+
+ // numRead < 0
+ return true;
}
@@ -488,8 +511,9 @@
zzReader = reader;
zzAtBOL = true;
zzAtEOF = false;
+ zzEOFDone = false;
zzEndRead = zzStartRead = 0;
- zzCurrentPos = zzMarkedPos = zzPushbackPos = 0;
+ zzCurrentPos = zzMarkedPos = 0;
yyline = yychar = yycolumn = 0;
zzLexicalState = YYINITIAL;
}
@@ -619,7 +643,7 @@
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
- zzState = zzLexicalState;
+ zzState = ZZ_LEXSTATE[zzLexicalState];
zzForAction: {
@@ -667,44 +691,44 @@
zzMarkedPos = zzMarkedPosL;
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
- case 4:
- { return HOST;
+ case 5:
+ { return NUM;
}
case 11: break;
case 9:
{ return ACRONYM;
}
case 12: break;
- case 8:
- { return ACRONYM_DEP;
+ case 7:
+ { return COMPANY;
}
case 13: break;
+ case 10:
+ { return EMAIL;
+ }
+ case 14: break;
case 1:
{ /* ignore */
}
- case 14: break;
- case 5:
- { return NUM;
+ case 15: break;
+ case 6:
+ { return APOSTROPHE;
}
- case 15: break;
+ case 16: break;
case 3:
{ return CJ;
}
- case 16: break;
- case 2:
- { return ALPHANUM;
- }
case 17: break;
- case 7:
- { return COMPANY;
+ case 8:
+ { return ACRONYM_DEP;
}
case 18: break;
- case 6:
- { return APOSTROPHE;
+ case 2:
+ { return ALPHANUM;
}
case 19: break;
- case 10:
- { return EMAIL;
+ case 4:
+ { return HOST;
}
case 20: break;
default:
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.jflex
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.jflex (revision 886325)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.jflex (working copy)
@@ -19,23 +19,19 @@
/*
-WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
- the tokenizer, only use Java 1.4 !!!
- This grammar currently uses constructs (eg :digit:, :letter:) whose
- meaning can vary according to the JRE used to run jflex. See
- https://issues.apache.org/jira/browse/LUCENE-1126 for details.
- For current backwards compatibility it is needed to support
- only Java 1.4 - this will change in Lucene 3.1.
+WARNING: if you change StandardTokenizerImpl*.jflex and need to regenerate
+ the tokenizer, only use the trunk version of JFlex 1.5 at the moment!
*/
-import org.apache.lucene.analysis.Token;
+import java.io.Reader;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
%%
-%class StandardTokenizerImpl
-%unicode
+%class StandardTokenizerImpl31
+%implements StandardTokenizerInterface
+%unicode 4.0
%integer
%function getNextToken
%pack
@@ -65,17 +61,21 @@
}
/**
- * Fills Lucene token with the current token text.
+ * Fills TermAttribute with the current token text.
*/
-final void getText(Token t) {
+public final void getText(TermAttribute t) {
t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}
/**
- * Fills TermAttribute with the current token text.
+ * Resets the Tokenizer to a new Reader.
*/
-final void getText(TermAttribute t) {
- t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
+public final void reset(Reader r) {
+ // reset to default buffer size, if buffer has grown
+ if (zzBuffer.length > ZZ_BUFFERSIZE) {
+ zzBuffer = new char[ZZ_BUFFERSIZE];
+ }
+ yyreset(r);
}
%}
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.java
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.java (revision 886325)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.java (working copy)
@@ -1,4 +1,4 @@
-/* The following code was generated by JFlex 1.4.1 on 9/4/08 6:49 PM */
+/* The following code was generated by JFlex 1.5.0-SNAPSHOT on 08.04.10 13:01 */
package org.apache.lucene.analysis.standard;
@@ -21,27 +21,22 @@
/*
-WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
- the tokenizer, only use Java 1.4 !!!
- This grammar currently uses constructs (eg :digit:, :letter:) whose
- meaning can vary according to the JRE used to run jflex. See
- https://issues.apache.org/jira/browse/LUCENE-1126 for details.
- For current backwards compatibility it is needed to support
- only Java 1.4 - this will change in Lucene 3.1.
+WARNING: if you change StandardTokenizerImpl*.jflex and need to regenerate
+ the tokenizer, only use the trunk version of JFlex 1.5 at the moment!
*/
-import org.apache.lucene.analysis.Token;
+import java.io.Reader;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
/**
* This class is a scanner generated by
- * JFlex 1.4.1
- * on 9/4/08 6:49 PM from the specification file
- * /tango/mike/src/lucene.standarddigit/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex
+ * JFlex 1.5.0-SNAPSHOT
+ * on 08.04.10 13:01 from the specification file
+ * C:/Users/Uwe Schindler/Projects/lucene/trunk-full1/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.jflex
*/
-class StandardTokenizerImpl {
+class StandardTokenizerImplOrig implements StandardTokenizerInterface {
/** This character denotes the end of file */
public static final int YYEOF = -1;
@@ -52,6 +47,16 @@
/** 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
+ };
+
/**
* Translates characters to character classes
*/
@@ -307,9 +312,6 @@
/** 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;
@@ -340,6 +342,9 @@
/** zzAtEOF == true <=> the scanner is at the EOF */
private boolean zzAtEOF;
+ /** denotes if the user-EOF-code has already been executed */
+ private boolean zzEOFDone;
+
/* user code: */
public static final int ALPHANUM = StandardTokenizer.ALPHANUM;
@@ -364,27 +369,32 @@
}
/**
- * Fills Lucene token with the current token text.
+ * Fills TermAttribute with the current token text.
*/
-final void getText(Token t) {
+public final void getText(TermAttribute t) {
t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}
/**
- * Fills TermAttribute with the current token text.
+ * Resets the Tokenizer to a new Reader.
*/
-final void getText(TermAttribute t) {
- t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
+public final void reset(Reader r) {
+ // reset to default buffer size, if buffer has grown
+ if (zzBuffer.length > ZZ_BUFFERSIZE) {
+ zzBuffer = new char[ZZ_BUFFERSIZE];
+ }
+ yyreset(r);
}
+
/**
* 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) {
+ StandardTokenizerImplOrig(java.io.Reader in) {
this.zzReader = in;
}
@@ -394,7 +404,7 @@
*
* @param in the java.io.Inputstream to read input from.
*/
- StandardTokenizerImpl(java.io.InputStream in) {
+ StandardTokenizerImplOrig(java.io.InputStream in) {
this(new java.io.InputStreamReader(in));
}
@@ -436,7 +446,6 @@
zzEndRead-= zzStartRead;
zzCurrentPos-= zzStartRead;
zzMarkedPos-= zzStartRead;
- zzPushbackPos-= zzStartRead;
zzStartRead = 0;
}
@@ -452,13 +461,23 @@
int numRead = zzReader.read(zzBuffer, zzEndRead,
zzBuffer.length-zzEndRead);
- if (numRead < 0) {
- return true;
- }
- else {
+ if (numRead > 0) {
zzEndRead+= numRead;
return false;
}
+ // unlikely but not impossible: read 0 characters, but not at end of stream
+ if (numRead == 0) {
+ int c = zzReader.read();
+ if (c == -1) {
+ return true;
+ } else {
+ zzBuffer[zzEndRead++] = (char) c;
+ return false;
+ }
+ }
+
+ // numRead < 0
+ return true;
}
@@ -488,8 +507,9 @@
zzReader = reader;
zzAtBOL = true;
zzAtEOF = false;
+ zzEOFDone = false;
zzEndRead = zzStartRead = 0;
- zzCurrentPos = zzMarkedPos = zzPushbackPos = 0;
+ zzCurrentPos = zzMarkedPos = 0;
yyline = yychar = yycolumn = 0;
zzLexicalState = YYINITIAL;
}
@@ -619,7 +639,7 @@
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
- zzState = zzLexicalState;
+ zzState = ZZ_LEXSTATE[zzLexicalState];
zzForAction: {
@@ -667,44 +687,44 @@
zzMarkedPos = zzMarkedPosL;
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
- case 4:
- { return HOST;
+ case 5:
+ { return NUM;
}
case 11: break;
case 9:
{ return ACRONYM;
}
case 12: break;
- case 8:
- { return ACRONYM_DEP;
+ case 7:
+ { return COMPANY;
}
case 13: break;
+ case 10:
+ { return EMAIL;
+ }
+ case 14: break;
case 1:
{ /* ignore */
}
- case 14: break;
- case 5:
- { return NUM;
+ case 15: break;
+ case 6:
+ { return APOSTROPHE;
}
- case 15: break;
+ case 16: break;
case 3:
{ return CJ;
}
- case 16: break;
- case 2:
- { return ALPHANUM;
- }
case 17: break;
- case 7:
- { return COMPANY;
+ case 8:
+ { return ACRONYM_DEP;
}
case 18: break;
- case 6:
- { return APOSTROPHE;
+ case 2:
+ { return ALPHANUM;
}
case 19: break;
- case 10:
- { return EMAIL;
+ case 4:
+ { return HOST;
}
case 20: break;
default:
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.jflex
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.jflex (revision 886325)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.jflex (working copy)
@@ -19,23 +19,19 @@
/*
-WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
- the tokenizer, only use Java 1.4 !!!
- This grammar currently uses constructs (eg :digit:, :letter:) whose
- meaning can vary according to the JRE used to run jflex. See
- https://issues.apache.org/jira/browse/LUCENE-1126 for details.
- For current backwards compatibility it is needed to support
- only Java 1.4 - this will change in Lucene 3.1.
+WARNING: if you change StandardTokenizerImpl*.jflex and need to regenerate
+ the tokenizer, only use the trunk version of JFlex 1.5 at the moment!
*/
-import org.apache.lucene.analysis.Token;
+import java.io.Reader;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
%%
-%class StandardTokenizerImpl
-%unicode
+%class StandardTokenizerImplOrig
+%implements StandardTokenizerInterface
+%unicode 3.0
%integer
%function getNextToken
%pack
@@ -65,17 +61,21 @@
}
/**
- * Fills Lucene token with the current token text.
+ * Fills TermAttribute with the current token text.
*/
-final void getText(Token t) {
+public final void getText(TermAttribute t) {
t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}
/**
- * Fills TermAttribute with the current token text.
+ * Resets the Tokenizer to a new Reader.
*/
-final void getText(TermAttribute t) {
- t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
+public final void reset(Reader r) {
+ // reset to default buffer size, if buffer has grown
+ if (zzBuffer.length > ZZ_BUFFERSIZE) {
+ zzBuffer = new char[ZZ_BUFFERSIZE];
+ }
+ yyreset(r);
}
%}
Index: src/java/org/apache/lucene/analysis/standard/StandardTokenizerInterface.java
===================================================================
--- src/java/org/apache/lucene/analysis/standard/StandardTokenizerInterface.java (revision 0)
+++ src/java/org/apache/lucene/analysis/standard/StandardTokenizerInterface.java (revision 0)
@@ -0,0 +1,66 @@
+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.tokenattributes.TermAttribute;
+
+import java.io.Reader;
+import java.io.IOException;
+
+interface StandardTokenizerInterface {
+
+ /** This character denotes the end of file */
+ public static final int YYEOF = -1;
+
+ /**
+ * Copies the matched text into the TermAttribute
+ */
+ void getText(TermAttribute t);
+
+ /**
+ * Returns the current position.
+ */
+ int yychar();
+
+ /**
+ * 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 ZZ_INITIAL.
+ *
+ * @param reader the new input stream
+ */
+ void reset(Reader reader);
+
+ /**
+ * Returns the length of the matched text region.
+ */
+ int yylength();
+
+ /**
+ * 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, {@link #YYEOF} on end of stream
+ * @exception IOException if any I/O-Error occurs
+ */
+ int getNextToken() throws IOException;
+
+}
Property changes on: src\java\org\apache\lucene\analysis\standard\StandardTokenizerInterface.java
___________________________________________________________________
Added: svn:keywords
+ Date Author Id Revision HeadURL
Added: svn:eol-style
+ native
Index: src/test/org/apache/lucene/analysis/TestStandardAnalyzer.java
===================================================================
--- src/test/org/apache/lucene/analysis/TestStandardAnalyzer.java (revision 931671)
+++ src/test/org/apache/lucene/analysis/TestStandardAnalyzer.java (working copy)
@@ -224,4 +224,12 @@
"