mirror of https://github.com/apache/lucene.git
LUCENE-2074: Refactor StandardTokenizer to have separate JFlex files per matchVersion. Also reset zzBuffer to initial size on reset(Reader) and clean up reset methods.
git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@932163 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Uwe Schindler
parent
81c21e163b
commit
be7da179ff
|
|
@ -237,6 +237,9 @@ Bug fixes
|
||||||
which caused corruption for sep codec. Also fixed several tests to
|
which caused corruption for sep codec. Also fixed several tests to
|
||||||
test all 4 core codecs. (Renaud Delbru via Mike McCandless)
|
test all 4 core codecs. (Renaud Delbru via Mike McCandless)
|
||||||
|
|
||||||
|
* LUCENE-2074: Reduce buffer size of lexer back to default on reset.
|
||||||
|
(Ruben Laguna, Shai Erera via Uwe Schindler)
|
||||||
|
|
||||||
New features
|
New features
|
||||||
|
|
||||||
* LUCENE-2128: Parallelized fetching document frequencies during weight
|
* LUCENE-2128: Parallelized fetching document frequencies during weight
|
||||||
|
|
@ -347,6 +350,9 @@ New features
|
||||||
can be used to prevent commits from ever getting deleted from the index.
|
can be used to prevent commits from ever getting deleted from the index.
|
||||||
(Shai Erera)
|
(Shai Erera)
|
||||||
|
|
||||||
|
* LUCENE-2074: Make StandardTokenizer fit for Unicode 4.0, if the
|
||||||
|
matchVersion parameter is Version.LUCENE_31. (Uwe Schindler)
|
||||||
|
|
||||||
Optimizations
|
Optimizations
|
||||||
|
|
||||||
* LUCENE-2075: Terms dict cache is now shared across threads instead
|
* LUCENE-2075: Terms dict cache is now shared across threads instead
|
||||||
|
|
@ -433,9 +439,12 @@ Build
|
||||||
into core, and moved the ICU-based collation support into contrib/icu.
|
into core, and moved the ICU-based collation support into contrib/icu.
|
||||||
(Robert Muir)
|
(Robert Muir)
|
||||||
|
|
||||||
* LUCENE-2326: Removed SVN checkouts for backwards tests. The backwards branch
|
* LUCENE-2326: Removed SVN checkouts for backwards tests. The backwards
|
||||||
is now included in the svn repository using "svn copy" after release.
|
branch is now included in the svn repository using "svn copy"
|
||||||
(Uwe Schindler)
|
after release. (Uwe Schindler)
|
||||||
|
|
||||||
|
* LUCENE-2074: Regenerating StandardTokenizerImpl files now needs
|
||||||
|
JFlex 1.5 (currently only available on SVN). (Uwe Schindler)
|
||||||
|
|
||||||
Test Cases
|
Test Cases
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -698,11 +698,14 @@ The source distribution does not contain sources of the previous Lucene Java ver
|
||||||
<target name="jflex" depends="clean-jflex,jflex-StandardAnalyzer" />
|
<target name="jflex" depends="clean-jflex,jflex-StandardAnalyzer" />
|
||||||
|
|
||||||
<target name="jflex-StandardAnalyzer" depends="init,jflex-check" if="jflex.present">
|
<target name="jflex-StandardAnalyzer" depends="init,jflex-check" if="jflex.present">
|
||||||
<taskdef classname="JFlex.anttask.JFlexTask" name="jflex">
|
<taskdef classname="jflex.anttask.JFlexTask" name="jflex">
|
||||||
<classpath location="${jflex.home}/lib/JFlex.jar" />
|
<classpath refid="jflex.classpath"/>
|
||||||
</taskdef>
|
</taskdef>
|
||||||
|
|
||||||
<jflex file="src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex"
|
<jflex file="src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.jflex"
|
||||||
|
outdir="src/java/org/apache/lucene/analysis/standard"
|
||||||
|
nobak="on" />
|
||||||
|
<jflex file="src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.jflex"
|
||||||
outdir="src/java/org/apache/lucene/analysis/standard"
|
outdir="src/java/org/apache/lucene/analysis/standard"
|
||||||
nobak="on" />
|
nobak="on" />
|
||||||
</target>
|
</target>
|
||||||
|
|
|
||||||
|
|
@ -92,6 +92,13 @@
|
||||||
<property name="javacc.home" location="${common.dir}"/>
|
<property name="javacc.home" location="${common.dir}"/>
|
||||||
<property name="jflex.home" location="${common.dir}"/>
|
<property name="jflex.home" location="${common.dir}"/>
|
||||||
|
|
||||||
|
<path id="jflex.classpath">
|
||||||
|
<fileset dir="${jflex.home}/">
|
||||||
|
<include name="**/target/*.jar"/>
|
||||||
|
<include name="**/lib/*.jar"/>
|
||||||
|
</fileset>
|
||||||
|
</path>
|
||||||
|
|
||||||
<property name="backwards.dir" location="backwards"/>
|
<property name="backwards.dir" location="backwards"/>
|
||||||
<property name="build.dir.backwards" location="${build.dir}/backwards"/>
|
<property name="build.dir.backwards" location="${build.dir}/backwards"/>
|
||||||
|
|
||||||
|
|
@ -151,11 +158,9 @@
|
||||||
classpath="${javacc.home}/bin/lib/javacc.jar"
|
classpath="${javacc.home}/bin/lib/javacc.jar"
|
||||||
/>
|
/>
|
||||||
|
|
||||||
<available
|
<available property="jflex.present" classname="jflex.anttask.JFlexTask">
|
||||||
property="jflex.present"
|
<classpath refid="jflex.classpath"/>
|
||||||
classname="JFlex.anttask.JFlexTask"
|
</available>
|
||||||
classpath="${jflex.home}/lib/JFlex.jar"
|
|
||||||
/>
|
|
||||||
|
|
||||||
<available
|
<available
|
||||||
property="maven.ant.tasks.present"
|
property="maven.ant.tasks.present"
|
||||||
|
|
@ -237,17 +242,17 @@
|
||||||
JFlex not found.
|
JFlex not found.
|
||||||
JFlex Home: ${jflex.home}
|
JFlex Home: ${jflex.home}
|
||||||
|
|
||||||
Please download and install JFlex from:
|
Please install the jFlex 1.5 version (currently not released)
|
||||||
|
from its SVN repository:
|
||||||
|
|
||||||
<http://jflex.de/download.html>
|
svn co http://jflex.svn.sourceforge.net/svnroot/jflex/trunk jflex
|
||||||
|
cd jflex
|
||||||
|
mvn install
|
||||||
|
|
||||||
Then, create a build.properties file either in your home
|
Then, create a build.properties file either in your home
|
||||||
directory, or within the Lucene directory and set the jflex.home
|
directory, or within the Lucene directory and set the jflex.home
|
||||||
property to the path where JFlex is installed. For example,
|
property to the path where the JFlex trunk checkout is located
|
||||||
if you installed JFlex in /usr/local/java/jflex-1.4.1, then set the
|
(in the above example its the directory called "jflex").
|
||||||
jflex.home property to:
|
|
||||||
|
|
||||||
jflex.home=/usr/local/java/jflex-1.4.1
|
|
||||||
|
|
||||||
##################################################################
|
##################################################################
|
||||||
</fail>
|
</fail>
|
||||||
|
|
|
||||||
|
|
@ -16,10 +16,5 @@
|
||||||
*/
|
*/
|
||||||
|
|
||||||
|
|
||||||
WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
|
WARNING: if you change StandardTokenizerImpl*.jflex and need to regenerate
|
||||||
the tokenizer, only use Java 1.4 !!!
|
the tokenizer, only use the trunk version of JFlex 1.5 at the moment!
|
||||||
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.
|
|
||||||
|
|
|
||||||
|
|
@ -34,12 +34,12 @@ public final class StandardFilter extends TokenFilter {
|
||||||
typeAtt = addAttribute(TypeAttribute.class);
|
typeAtt = addAttribute(TypeAttribute.class);
|
||||||
}
|
}
|
||||||
|
|
||||||
private static final String APOSTROPHE_TYPE = StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.APOSTROPHE];
|
private static final String APOSTROPHE_TYPE = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.APOSTROPHE];
|
||||||
private static final String ACRONYM_TYPE = StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.ACRONYM];
|
private static final String ACRONYM_TYPE = StandardTokenizer.TOKEN_TYPES[StandardTokenizer.ACRONYM];
|
||||||
|
|
||||||
// this filters uses attribute type
|
// this filters uses attribute type
|
||||||
private TypeAttribute typeAtt;
|
private final TypeAttribute typeAtt;
|
||||||
private TermAttribute termAtt;
|
private final TermAttribute termAtt;
|
||||||
|
|
||||||
/** Returns the next token in the stream, or null at EOS.
|
/** Returns the next token in the stream, or null at EOS.
|
||||||
* <p>Removes <tt>'s</tt> from the end of words.
|
* <p>Removes <tt>'s</tt> from the end of words.
|
||||||
|
|
|
||||||
|
|
@ -23,7 +23,7 @@ import java.io.Reader;
|
||||||
import org.apache.lucene.analysis.Tokenizer;
|
import org.apache.lucene.analysis.Tokenizer;
|
||||||
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
|
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
|
||||||
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
|
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
|
||||||
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
|
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
|
||||||
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
|
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
|
||||||
import org.apache.lucene.util.AttributeSource;
|
import org.apache.lucene.util.AttributeSource;
|
||||||
import org.apache.lucene.util.Version;
|
import org.apache.lucene.util.Version;
|
||||||
|
|
@ -55,7 +55,7 @@ import org.apache.lucene.util.Version;
|
||||||
|
|
||||||
public final class StandardTokenizer extends Tokenizer {
|
public final class StandardTokenizer extends Tokenizer {
|
||||||
/** A private instance of the JFlex-constructed scanner */
|
/** 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 ALPHANUM = 0;
|
||||||
public static final int APOSTROPHE = 1;
|
public static final int APOSTROPHE = 1;
|
||||||
|
|
@ -111,7 +111,6 @@ public final class StandardTokenizer extends Tokenizer {
|
||||||
*/
|
*/
|
||||||
public StandardTokenizer(Version matchVersion, Reader input) {
|
public StandardTokenizer(Version matchVersion, Reader input) {
|
||||||
super();
|
super();
|
||||||
this.scanner = new StandardTokenizerImpl(input);
|
|
||||||
init(input, matchVersion);
|
init(input, matchVersion);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -120,7 +119,6 @@ public final class StandardTokenizer extends Tokenizer {
|
||||||
*/
|
*/
|
||||||
public StandardTokenizer(Version matchVersion, AttributeSource source, Reader input) {
|
public StandardTokenizer(Version matchVersion, AttributeSource source, Reader input) {
|
||||||
super(source);
|
super(source);
|
||||||
this.scanner = new StandardTokenizerImpl(input);
|
|
||||||
init(input, matchVersion);
|
init(input, matchVersion);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -129,29 +127,26 @@ public final class StandardTokenizer extends Tokenizer {
|
||||||
*/
|
*/
|
||||||
public StandardTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
|
public StandardTokenizer(Version matchVersion, AttributeFactory factory, Reader input) {
|
||||||
super(factory);
|
super(factory);
|
||||||
this.scanner = new StandardTokenizerImpl(input);
|
|
||||||
init(input, matchVersion);
|
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)) {
|
if (matchVersion.onOrAfter(Version.LUCENE_24)) {
|
||||||
replaceInvalidAcronym = true;
|
replaceInvalidAcronym = true;
|
||||||
} else {
|
} else {
|
||||||
replaceInvalidAcronym = false;
|
replaceInvalidAcronym = false;
|
||||||
}
|
}
|
||||||
this.input = input;
|
this.input = input;
|
||||||
termAtt = addAttribute(TermAttribute.class);
|
|
||||||
offsetAtt = addAttribute(OffsetAttribute.class);
|
|
||||||
posIncrAtt = addAttribute(PositionIncrementAttribute.class);
|
|
||||||
typeAtt = addAttribute(TypeAttribute.class);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// this tokenizer generates three attributes:
|
// this tokenizer generates three attributes:
|
||||||
// offset, positionIncrement and type
|
// term offset, positionIncrement and type
|
||||||
private TermAttribute termAtt;
|
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
|
||||||
private OffsetAttribute offsetAtt;
|
private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
|
||||||
private PositionIncrementAttribute posIncrAtt;
|
private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
|
||||||
private TypeAttribute typeAtt;
|
private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* (non-Javadoc)
|
* (non-Javadoc)
|
||||||
|
|
@ -166,7 +161,7 @@ public final class StandardTokenizer extends Tokenizer {
|
||||||
while(true) {
|
while(true) {
|
||||||
int tokenType = scanner.getNextToken();
|
int tokenType = scanner.getNextToken();
|
||||||
|
|
||||||
if (tokenType == StandardTokenizerImpl.YYEOF) {
|
if (tokenType == StandardTokenizerInterface.YYEOF) {
|
||||||
return false;
|
return false;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -174,19 +169,19 @@ public final class StandardTokenizer extends Tokenizer {
|
||||||
posIncrAtt.setPositionIncrement(posIncr);
|
posIncrAtt.setPositionIncrement(posIncr);
|
||||||
scanner.getText(termAtt);
|
scanner.getText(termAtt);
|
||||||
final int start = scanner.yychar();
|
final int start = scanner.yychar();
|
||||||
offsetAtt.setOffset(correctOffset(start), correctOffset(start+termAtt.termLength()));
|
offsetAtt.setOffset(correctOffset(start), correctOffset(start+termAtt.length()));
|
||||||
// This 'if' should be removed in the next release. For now, it converts
|
// This 'if' should be removed in the next release. For now, it converts
|
||||||
// invalid acronyms to HOST. When removed, only the 'else' part should
|
// invalid acronyms to HOST. When removed, only the 'else' part should
|
||||||
// remain.
|
// remain.
|
||||||
if (tokenType == StandardTokenizerImpl.ACRONYM_DEP) {
|
if (tokenType == StandardTokenizer.ACRONYM_DEP) {
|
||||||
if (replaceInvalidAcronym) {
|
if (replaceInvalidAcronym) {
|
||||||
typeAtt.setType(StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.HOST]);
|
typeAtt.setType(StandardTokenizer.TOKEN_TYPES[StandardTokenizer.HOST]);
|
||||||
termAtt.setTermLength(termAtt.termLength() - 1); // remove extra '.'
|
termAtt.setLength(termAtt.length() - 1); // remove extra '.'
|
||||||
} else {
|
} else {
|
||||||
typeAtt.setType(StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.ACRONYM]);
|
typeAtt.setType(StandardTokenizer.TOKEN_TYPES[StandardTokenizer.ACRONYM]);
|
||||||
}
|
}
|
||||||
} else {
|
} else {
|
||||||
typeAtt.setType(StandardTokenizerImpl.TOKEN_TYPES[tokenType]);
|
typeAtt.setType(StandardTokenizer.TOKEN_TYPES[tokenType]);
|
||||||
}
|
}
|
||||||
return true;
|
return true;
|
||||||
} else
|
} else
|
||||||
|
|
@ -203,21 +198,10 @@ public final class StandardTokenizer extends Tokenizer {
|
||||||
offsetAtt.setOffset(finalOffset, finalOffset);
|
offsetAtt.setOffset(finalOffset, finalOffset);
|
||||||
}
|
}
|
||||||
|
|
||||||
/*
|
|
||||||
* (non-Javadoc)
|
|
||||||
*
|
|
||||||
* @see org.apache.lucene.analysis.TokenStream#reset()
|
|
||||||
*/
|
|
||||||
@Override
|
|
||||||
public void reset() throws IOException {
|
|
||||||
super.reset();
|
|
||||||
scanner.yyreset(input);
|
|
||||||
}
|
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public void reset(Reader reader) throws IOException {
|
public void reset(Reader reader) throws IOException {
|
||||||
super.reset(reader);
|
super.reset(reader);
|
||||||
reset();
|
scanner.reset(reader);
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,747 @@
|
||||||
|
/* The following code was generated by JFlex 1.5.0-SNAPSHOT on 09.04.10 00:10 */
|
||||||
|
|
||||||
|
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 the trunk version of JFlex 1.5 at the moment!
|
||||||
|
|
||||||
|
*/
|
||||||
|
|
||||||
|
import java.io.Reader;
|
||||||
|
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* This class is a scanner generated by
|
||||||
|
* <a href="http://www.jflex.de/">JFlex</a> 1.5.0-SNAPSHOT
|
||||||
|
* on 09.04.10 00:10 from the specification file
|
||||||
|
* <tt>C:/Users/Uwe Schindler/Projects/lucene/trunk-full1/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl31.jflex</tt>
|
||||||
|
*/
|
||||||
|
class StandardTokenizerImpl31 implements StandardTokenizerInterface {
|
||||||
|
|
||||||
|
/** 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
|
||||||
|
};
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 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\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\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";
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 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 <code>aState</code>
|
||||||
|
*/
|
||||||
|
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 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;
|
||||||
|
|
||||||
|
/** denotes if the user-EOF-code has already been executed */
|
||||||
|
private boolean zzEOFDone;
|
||||||
|
|
||||||
|
/* 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.
|
||||||
|
*/
|
||||||
|
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 CharTermAttribute with the current token text.
|
||||||
|
*/
|
||||||
|
public final void getText(CharTermAttribute t) {
|
||||||
|
t.copyBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Resets the Tokenizer to a new Reader.
|
||||||
|
*/
|
||||||
|
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.
|
||||||
|
*/
|
||||||
|
StandardTokenizerImpl31(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.
|
||||||
|
*/
|
||||||
|
StandardTokenizerImpl31(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 < 1234) {
|
||||||
|
int count = packed.charAt(i++);
|
||||||
|
char value = packed.charAt(i++);
|
||||||
|
do map[j++] = value; while (--count > 0);
|
||||||
|
}
|
||||||
|
return map;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Refills the input buffer.
|
||||||
|
*
|
||||||
|
* @return <code>false</code>, 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;
|
||||||
|
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) {
|
||||||
|
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;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 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
|
||||||
|
* <b>cannot</b> be reused (internal buffer is discarded and lost).
|
||||||
|
* Lexical state is set to <tt>ZZ_INITIAL</tt>.
|
||||||
|
*
|
||||||
|
* @param reader the new input stream
|
||||||
|
*/
|
||||||
|
public final void yyreset(java.io.Reader reader) {
|
||||||
|
zzReader = reader;
|
||||||
|
zzAtBOL = true;
|
||||||
|
zzAtEOF = false;
|
||||||
|
zzEOFDone = false;
|
||||||
|
zzEndRead = zzStartRead = 0;
|
||||||
|
zzCurrentPos = zzMarkedPos = 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 <tt>pos</tt> from the
|
||||||
|
* matched text.
|
||||||
|
*
|
||||||
|
* It is equivalent to yytext().charAt(pos), but faster
|
||||||
|
*
|
||||||
|
* @param pos the position of the character to fetch.
|
||||||
|
* A value from 0 to yylength()-1.
|
||||||
|
*
|
||||||
|
* @return the character at position pos
|
||||||
|
*/
|
||||||
|
public final char yycharat(int pos) {
|
||||||
|
return zzBuffer[zzStartRead+pos];
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Returns the length of the matched text region.
|
||||||
|
*/
|
||||||
|
public final int yylength() {
|
||||||
|
return zzMarkedPos-zzStartRead;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Reports an error that occured while scanning.
|
||||||
|
*
|
||||||
|
* In a wellformed scanner (no or only correct usage of
|
||||||
|
* yypushback(int) and a match-all fallback rule) this method
|
||||||
|
* will only be called with things that "Can't Possibly Happen".
|
||||||
|
* If this method is called, something is seriously wrong
|
||||||
|
* (e.g. a JFlex bug producing a faulty scanner etc.).
|
||||||
|
*
|
||||||
|
* Usual syntax/scanner level error handling should be done
|
||||||
|
* in error fallback rules.
|
||||||
|
*
|
||||||
|
* @param errorCode the code of the errormessage to display
|
||||||
|
*/
|
||||||
|
private void zzScanError(int errorCode) {
|
||||||
|
String message;
|
||||||
|
try {
|
||||||
|
message = ZZ_ERROR_MSG[errorCode];
|
||||||
|
}
|
||||||
|
catch (ArrayIndexOutOfBoundsException e) {
|
||||||
|
message = ZZ_ERROR_MSG[ZZ_UNKNOWN_ERROR];
|
||||||
|
}
|
||||||
|
|
||||||
|
throw new Error(message);
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Pushes the specified amount of characters back into the input stream.
|
||||||
|
*
|
||||||
|
* They will be read again by then next call of the scanning method
|
||||||
|
*
|
||||||
|
* @param number the number of characters to be read again.
|
||||||
|
* This number must not be greater than yylength()!
|
||||||
|
*/
|
||||||
|
public void yypushback(int number) {
|
||||||
|
if ( number > yylength() )
|
||||||
|
zzScanError(ZZ_PUSHBACK_2BIG);
|
||||||
|
|
||||||
|
zzMarkedPos -= number;
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Resumes scanning until the next regular expression is matched,
|
||||||
|
* the end of input is encountered or an I/O-Error occurs.
|
||||||
|
*
|
||||||
|
* @return the next token
|
||||||
|
* @exception java.io.IOException if any I/O-Error occurs
|
||||||
|
*/
|
||||||
|
public 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 = ZZ_LEXSTATE[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 5:
|
||||||
|
{ return NUM;
|
||||||
|
}
|
||||||
|
case 11: break;
|
||||||
|
case 9:
|
||||||
|
{ return ACRONYM;
|
||||||
|
}
|
||||||
|
case 12: break;
|
||||||
|
case 7:
|
||||||
|
{ return COMPANY;
|
||||||
|
}
|
||||||
|
case 13: break;
|
||||||
|
case 10:
|
||||||
|
{ return EMAIL;
|
||||||
|
}
|
||||||
|
case 14: break;
|
||||||
|
case 1:
|
||||||
|
{ /* ignore */
|
||||||
|
}
|
||||||
|
case 15: break;
|
||||||
|
case 6:
|
||||||
|
{ return APOSTROPHE;
|
||||||
|
}
|
||||||
|
case 16: break;
|
||||||
|
case 3:
|
||||||
|
{ return CJ;
|
||||||
|
}
|
||||||
|
case 17: break;
|
||||||
|
case 8:
|
||||||
|
{ return ACRONYM_DEP;
|
||||||
|
}
|
||||||
|
case 18: break;
|
||||||
|
case 2:
|
||||||
|
{ return ALPHANUM;
|
||||||
|
}
|
||||||
|
case 19: break;
|
||||||
|
case 4:
|
||||||
|
{ return HOST;
|
||||||
|
}
|
||||||
|
case 20: break;
|
||||||
|
default:
|
||||||
|
if (zzInput == YYEOF && zzStartRead == zzCurrentPos) {
|
||||||
|
zzAtEOF = true;
|
||||||
|
return YYEOF;
|
||||||
|
}
|
||||||
|
else {
|
||||||
|
zzScanError(ZZ_NO_MATCH);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
}
|
||||||
|
|
@ -19,23 +19,19 @@ package org.apache.lucene.analysis.standard;
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
|
||||||
WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
|
WARNING: if you change StandardTokenizerImpl*.jflex and need to regenerate
|
||||||
the tokenizer, only use Java 1.4 !!!
|
the tokenizer, only use the trunk version of JFlex 1.5 at the moment!
|
||||||
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 java.io.Reader;
|
||||||
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
|
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
|
||||||
|
|
||||||
%%
|
%%
|
||||||
|
|
||||||
%class StandardTokenizerImpl
|
%class StandardTokenizerImpl31
|
||||||
%unicode
|
%implements StandardTokenizerInterface
|
||||||
|
%unicode 4.0
|
||||||
%integer
|
%integer
|
||||||
%function getNextToken
|
%function getNextToken
|
||||||
%pack
|
%pack
|
||||||
|
|
@ -55,7 +51,6 @@ public static final int CJ = StandardTokenizer.CJ;
|
||||||
* @deprecated this solves a bug where HOSTs that end with '.' are identified
|
* @deprecated this solves a bug where HOSTs that end with '.' are identified
|
||||||
* as ACRONYMs.
|
* as ACRONYMs.
|
||||||
*/
|
*/
|
||||||
@Deprecated
|
|
||||||
public static final int ACRONYM_DEP = StandardTokenizer.ACRONYM_DEP;
|
public static final int ACRONYM_DEP = StandardTokenizer.ACRONYM_DEP;
|
||||||
|
|
||||||
public static final String [] TOKEN_TYPES = StandardTokenizer.TOKEN_TYPES;
|
public static final String [] TOKEN_TYPES = StandardTokenizer.TOKEN_TYPES;
|
||||||
|
|
@ -66,17 +61,21 @@ public final int yychar()
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Fills Lucene token with the current token text.
|
* Fills CharTermAttribute with the current token text.
|
||||||
*/
|
*/
|
||||||
final void getText(Token t) {
|
public final void getText(CharTermAttribute t) {
|
||||||
t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
|
t.copyBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Fills TermAttribute with the current token text.
|
* Resets the Tokenizer to a new Reader.
|
||||||
*/
|
*/
|
||||||
final void getText(TermAttribute t) {
|
public final void reset(Reader r) {
|
||||||
t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
|
// reset to default buffer size, if buffer has grown
|
||||||
|
if (zzBuffer.length > ZZ_BUFFERSIZE) {
|
||||||
|
zzBuffer = new char[ZZ_BUFFERSIZE];
|
||||||
|
}
|
||||||
|
yyreset(r);
|
||||||
}
|
}
|
||||||
|
|
||||||
%}
|
%}
|
||||||
|
|
@ -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 09.04.10 00:10 */
|
||||||
|
|
||||||
package org.apache.lucene.analysis.standard;
|
package org.apache.lucene.analysis.standard;
|
||||||
|
|
||||||
|
|
@ -21,27 +21,22 @@ package org.apache.lucene.analysis.standard;
|
||||||
|
|
||||||
/*
|
/*
|
||||||
|
|
||||||
WARNING: if you change StandardTokenizerImpl.jflex and need to regenerate
|
WARNING: if you change StandardTokenizerImpl*.jflex and need to regenerate
|
||||||
the tokenizer, only use Java 1.4 !!!
|
the tokenizer, only use the trunk version of JFlex 1.5 at the moment!
|
||||||
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 java.io.Reader;
|
||||||
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
|
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
|
||||||
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* This class is a scanner generated by
|
* This class is a scanner generated by
|
||||||
* <a href="http://www.jflex.de/">JFlex</a> 1.4.1
|
* <a href="http://www.jflex.de/">JFlex</a> 1.5.0-SNAPSHOT
|
||||||
* on 9/4/08 6:49 PM from the specification file
|
* on 09.04.10 00:10 from the specification file
|
||||||
* <tt>/tango/mike/src/lucene.standarddigit/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImpl.jflex</tt>
|
* <tt>C:/Users/Uwe Schindler/Projects/lucene/trunk-full1/src/java/org/apache/lucene/analysis/standard/StandardTokenizerImplOrig.jflex</tt>
|
||||||
*/
|
*/
|
||||||
class StandardTokenizerImpl {
|
class StandardTokenizerImplOrig implements StandardTokenizerInterface {
|
||||||
|
|
||||||
/** This character denotes the end of file */
|
/** This character denotes the end of file */
|
||||||
public static final int YYEOF = -1;
|
public static final int YYEOF = -1;
|
||||||
|
|
@ -52,6 +47,16 @@ class StandardTokenizerImpl {
|
||||||
/** lexical states */
|
/** lexical states */
|
||||||
public static final int YYINITIAL = 0;
|
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
|
* Translates characters to character classes
|
||||||
*/
|
*/
|
||||||
|
|
@ -307,9 +312,6 @@ class StandardTokenizerImpl {
|
||||||
/** the textposition at the last accepting state */
|
/** the textposition at the last accepting state */
|
||||||
private int zzMarkedPos;
|
private int zzMarkedPos;
|
||||||
|
|
||||||
/** the textposition at the last state to be included in yytext */
|
|
||||||
private int zzPushbackPos;
|
|
||||||
|
|
||||||
/** the current text position in the buffer */
|
/** the current text position in the buffer */
|
||||||
private int zzCurrentPos;
|
private int zzCurrentPos;
|
||||||
|
|
||||||
|
|
@ -340,6 +342,9 @@ class StandardTokenizerImpl {
|
||||||
/** zzAtEOF == true <=> the scanner is at the EOF */
|
/** zzAtEOF == true <=> the scanner is at the EOF */
|
||||||
private boolean zzAtEOF;
|
private boolean zzAtEOF;
|
||||||
|
|
||||||
|
/** denotes if the user-EOF-code has already been executed */
|
||||||
|
private boolean zzEOFDone;
|
||||||
|
|
||||||
/* user code: */
|
/* user code: */
|
||||||
|
|
||||||
public static final int ALPHANUM = StandardTokenizer.ALPHANUM;
|
public static final int ALPHANUM = StandardTokenizer.ALPHANUM;
|
||||||
|
|
@ -354,7 +359,6 @@ public static final int CJ = StandardTokenizer.CJ;
|
||||||
* @deprecated this solves a bug where HOSTs that end with '.' are identified
|
* @deprecated this solves a bug where HOSTs that end with '.' are identified
|
||||||
* as ACRONYMs.
|
* as ACRONYMs.
|
||||||
*/
|
*/
|
||||||
@Deprecated
|
|
||||||
public static final int ACRONYM_DEP = StandardTokenizer.ACRONYM_DEP;
|
public static final int ACRONYM_DEP = StandardTokenizer.ACRONYM_DEP;
|
||||||
|
|
||||||
public static final String [] TOKEN_TYPES = StandardTokenizer.TOKEN_TYPES;
|
public static final String [] TOKEN_TYPES = StandardTokenizer.TOKEN_TYPES;
|
||||||
|
|
@ -365,27 +369,32 @@ public final int yychar()
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Fills Lucene token with the current token text.
|
* Fills CharTermAttribute with the current token text.
|
||||||
*/
|
*/
|
||||||
final void getText(Token t) {
|
public final void getText(CharTermAttribute t) {
|
||||||
t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
|
t.copyBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Fills TermAttribute with the current token text.
|
* Resets the Tokenizer to a new Reader.
|
||||||
*/
|
*/
|
||||||
final void getText(TermAttribute t) {
|
public final void reset(Reader r) {
|
||||||
t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
|
// 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
|
* Creates a new scanner
|
||||||
* There is also a java.io.InputStream version of this constructor.
|
* There is also a java.io.InputStream version of this constructor.
|
||||||
*
|
*
|
||||||
* @param in the java.io.Reader to read input from.
|
* @param in the java.io.Reader to read input from.
|
||||||
*/
|
*/
|
||||||
StandardTokenizerImpl(java.io.Reader in) {
|
StandardTokenizerImplOrig(java.io.Reader in) {
|
||||||
this.zzReader = in;
|
this.zzReader = in;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -395,7 +404,7 @@ final void getText(TermAttribute t) {
|
||||||
*
|
*
|
||||||
* @param in the java.io.Inputstream to read input from.
|
* @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));
|
this(new java.io.InputStreamReader(in));
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -437,7 +446,6 @@ final void getText(TermAttribute t) {
|
||||||
zzEndRead-= zzStartRead;
|
zzEndRead-= zzStartRead;
|
||||||
zzCurrentPos-= zzStartRead;
|
zzCurrentPos-= zzStartRead;
|
||||||
zzMarkedPos-= zzStartRead;
|
zzMarkedPos-= zzStartRead;
|
||||||
zzPushbackPos-= zzStartRead;
|
|
||||||
zzStartRead = 0;
|
zzStartRead = 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
@ -453,13 +461,23 @@ final void getText(TermAttribute t) {
|
||||||
int numRead = zzReader.read(zzBuffer, zzEndRead,
|
int numRead = zzReader.read(zzBuffer, zzEndRead,
|
||||||
zzBuffer.length-zzEndRead);
|
zzBuffer.length-zzEndRead);
|
||||||
|
|
||||||
if (numRead < 0) {
|
if (numRead > 0) {
|
||||||
return true;
|
|
||||||
}
|
|
||||||
else {
|
|
||||||
zzEndRead+= numRead;
|
zzEndRead+= numRead;
|
||||||
return false;
|
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;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|
@ -489,8 +507,9 @@ final void getText(TermAttribute t) {
|
||||||
zzReader = reader;
|
zzReader = reader;
|
||||||
zzAtBOL = true;
|
zzAtBOL = true;
|
||||||
zzAtEOF = false;
|
zzAtEOF = false;
|
||||||
|
zzEOFDone = false;
|
||||||
zzEndRead = zzStartRead = 0;
|
zzEndRead = zzStartRead = 0;
|
||||||
zzCurrentPos = zzMarkedPos = zzPushbackPos = 0;
|
zzCurrentPos = zzMarkedPos = 0;
|
||||||
yyline = yychar = yycolumn = 0;
|
yyline = yychar = yycolumn = 0;
|
||||||
zzLexicalState = YYINITIAL;
|
zzLexicalState = YYINITIAL;
|
||||||
}
|
}
|
||||||
|
|
@ -620,7 +639,7 @@ final void getText(TermAttribute t) {
|
||||||
|
|
||||||
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
|
zzCurrentPosL = zzCurrentPos = zzStartRead = zzMarkedPosL;
|
||||||
|
|
||||||
zzState = zzLexicalState;
|
zzState = ZZ_LEXSTATE[zzLexicalState];
|
||||||
|
|
||||||
|
|
||||||
zzForAction: {
|
zzForAction: {
|
||||||
|
|
@ -668,44 +687,44 @@ final void getText(TermAttribute t) {
|
||||||
zzMarkedPos = zzMarkedPosL;
|
zzMarkedPos = zzMarkedPosL;
|
||||||
|
|
||||||
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
|
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
|
||||||
case 4:
|
case 5:
|
||||||
{ return HOST;
|
{ return NUM;
|
||||||
}
|
}
|
||||||
case 11: break;
|
case 11: break;
|
||||||
case 9:
|
case 9:
|
||||||
{ return ACRONYM;
|
{ return ACRONYM;
|
||||||
}
|
}
|
||||||
case 12: break;
|
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:
|
case 7:
|
||||||
{ return COMPANY;
|
{ return COMPANY;
|
||||||
}
|
}
|
||||||
case 18: break;
|
case 13: break;
|
||||||
|
case 10:
|
||||||
|
{ return EMAIL;
|
||||||
|
}
|
||||||
|
case 14: break;
|
||||||
|
case 1:
|
||||||
|
{ /* ignore */
|
||||||
|
}
|
||||||
|
case 15: break;
|
||||||
case 6:
|
case 6:
|
||||||
{ return APOSTROPHE;
|
{ return APOSTROPHE;
|
||||||
}
|
}
|
||||||
|
case 16: break;
|
||||||
|
case 3:
|
||||||
|
{ return CJ;
|
||||||
|
}
|
||||||
|
case 17: break;
|
||||||
|
case 8:
|
||||||
|
{ return ACRONYM_DEP;
|
||||||
|
}
|
||||||
|
case 18: break;
|
||||||
|
case 2:
|
||||||
|
{ return ALPHANUM;
|
||||||
|
}
|
||||||
case 19: break;
|
case 19: break;
|
||||||
case 10:
|
case 4:
|
||||||
{ return EMAIL;
|
{ return HOST;
|
||||||
}
|
}
|
||||||
case 20: break;
|
case 20: break;
|
||||||
default:
|
default:
|
||||||
|
|
@ -0,0 +1,145 @@
|
||||||
|
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 the trunk version of JFlex 1.5 at the moment!
|
||||||
|
|
||||||
|
*/
|
||||||
|
|
||||||
|
import java.io.Reader;
|
||||||
|
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
|
||||||
|
|
||||||
|
%%
|
||||||
|
|
||||||
|
%class StandardTokenizerImplOrig
|
||||||
|
%implements StandardTokenizerInterface
|
||||||
|
%unicode 3.0
|
||||||
|
%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.
|
||||||
|
*/
|
||||||
|
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 CharTermAttribute with the current token text.
|
||||||
|
*/
|
||||||
|
public final void getText(CharTermAttribute t) {
|
||||||
|
t.copyBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Resets the Tokenizer to a new Reader.
|
||||||
|
*/
|
||||||
|
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);
|
||||||
|
}
|
||||||
|
|
||||||
|
%}
|
||||||
|
|
||||||
|
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 <a> not matched by <b> is !(!<a>|<b>)"
|
||||||
|
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 */ }
|
||||||
|
|
@ -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.CharTermAttribute;
|
||||||
|
|
||||||
|
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 CharTermAttribute
|
||||||
|
*/
|
||||||
|
void getText(CharTermAttribute 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
|
||||||
|
* <b>cannot</b> be reused (internal buffer is discarded and lost).
|
||||||
|
* Lexical state is set to <tt>ZZ_INITIAL</tt>.
|
||||||
|
*
|
||||||
|
* @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;
|
||||||
|
|
||||||
|
}
|
||||||
|
|
@ -224,4 +224,12 @@ public class TestStandardAnalyzer extends BaseTokenStreamTestCase {
|
||||||
"<ALPHANUM>", "<NUM>", "<HOST>", "<NUM>", "<ALPHANUM>",
|
"<ALPHANUM>", "<NUM>", "<HOST>", "<NUM>", "<ALPHANUM>",
|
||||||
"<ALPHANUM>", "<HOST>"});
|
"<ALPHANUM>", "<HOST>"});
|
||||||
}
|
}
|
||||||
|
|
||||||
|
public void testJava14BWCompatibility() throws Exception {
|
||||||
|
StandardAnalyzer sa = new StandardAnalyzer(Version.LUCENE_30);
|
||||||
|
assertAnalyzesTo(sa, "test\u02C6test", new String[] { "test", "test" });
|
||||||
|
sa = new StandardAnalyzer(Version.LUCENE_31);
|
||||||
|
assertAnalyzesTo(sa, "test\u02C6test", new String[] { "test\u02C6test" });
|
||||||
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue