You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2014/07/31 00:16:21 UTC
svn commit: r1614778 [3/9] - in /lucene/dev/trunk:
lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/
lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/
lucene/analysis/common/src/java/org/apache/lucene/analysis/br/
lucene/analy...
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/KeepWordFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/KeepWordFilterFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/KeepWordFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/KeepWordFilterFactory.java Wed Jul 30 22:16:16 2014
@@ -44,7 +44,6 @@ public class KeepWordFilterFactory exten
/** Creates a new KeepWordFilterFactory */
public KeepWordFilterFactory(Map<String,String> args) {
super(args);
- assureMatchVersion();
wordFiles = get(args, "words");
ignoreCase = getBoolean(args, "ignoreCase", false);
if (!args.isEmpty()) {
@@ -73,7 +72,7 @@ public class KeepWordFilterFactory exten
if (words == null) {
return input;
} else {
- final TokenStream filter = new KeepWordFilter(luceneMatchVersion, input, words);
+ final TokenStream filter = new KeepWordFilter(input, words);
return filter;
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilter.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilter.java Wed Jul 30 22:16:16 2014
@@ -20,7 +20,6 @@ package org.apache.lucene.analysis.misce
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.util.FilteringTokenFilter;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
-import org.apache.lucene.util.Version;
/**
* Removes words that are too long or too short from the stream.
@@ -39,13 +38,12 @@ public final class LengthFilter extends
* Create a new {@link LengthFilter}. This will filter out tokens whose
* {@link CharTermAttribute} is either too short ({@link CharTermAttribute#length()}
* < min) or too long ({@link CharTermAttribute#length()} > max).
- * @param version the Lucene match version
* @param in the {@link TokenStream} to consume
* @param min the minimum length
* @param max the maximum length
*/
- public LengthFilter(Version version, TokenStream in, int min, int max) {
- super(version, in);
+ public LengthFilter(TokenStream in, int min, int max) {
+ super(in);
if (min < 0) {
throw new IllegalArgumentException("minimum length must be greater than or equal to zero");
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilterFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilterFactory.java Wed Jul 30 22:16:16 2014
@@ -50,7 +50,7 @@ public class LengthFilterFactory extends
@Override
public LengthFilter create(TokenStream input) {
- final LengthFilter filter = new LengthFilter(luceneMatchVersion, input,min,max);
+ final LengthFilter filter = new LengthFilter(input,min,max);
return filter;
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/RemoveDuplicatesTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/RemoveDuplicatesTokenFilter.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/RemoveDuplicatesTokenFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/RemoveDuplicatesTokenFilter.java Wed Jul 30 22:16:16 2014
@@ -22,7 +22,6 @@ import org.apache.lucene.analysis.TokenS
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
-import org.apache.lucene.util.Version;
import java.io.IOException;
@@ -34,8 +33,7 @@ public final class RemoveDuplicatesToken
private final CharTermAttribute termAttribute = addAttribute(CharTermAttribute.class);
private final PositionIncrementAttribute posIncAttribute = addAttribute(PositionIncrementAttribute.class);
- // use a fixed version, as we don't care about case sensitivity.
- private final CharArraySet previous = new CharArraySet(Version.LUCENE_CURRENT, 8, false);
+ private final CharArraySet previous = new CharArraySet(8, false);
/**
* Creates a new RemoveDuplicatesTokenFilter
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilter.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilter.java Wed Jul 30 22:16:16 2014
@@ -20,15 +20,11 @@ package org.apache.lucene.analysis.misce
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
-import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.util.Version;
import java.io.IOException;
/**
* Trims leading and trailing whitespace from Tokens in the stream.
- * <p>As of Lucene 4.4, this filter does not support updateOffsets=true anymore
- * as it can lead to broken token streams.
*/
public final class TrimFilter extends TokenFilter {
@@ -36,10 +32,9 @@ public final class TrimFilter extends To
/**
* Create a new {@link TrimFilter}.
- * @param version the Lucene match version
* @param in the stream to consume
*/
- public TrimFilter(Version version, TokenStream in) {
+ public TrimFilter(TokenStream in) {
super(in);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilterFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilterFactory.java Wed Jul 30 22:16:16 2014
@@ -47,7 +47,7 @@ public class TrimFilterFactory extends T
@Override
public TrimFilter create(TokenStream input) {
- final TrimFilter filter = new TrimFilter(luceneMatchVersion, input);
+ final TrimFilter filter = new TrimFilter(input);
return filter;
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java Wed Jul 30 22:16:16 2014
@@ -80,7 +80,7 @@ public final class EdgeNGramTokenFilter
}
this.charUtils = version.onOrAfter(Version.LUCENE_4_4)
- ? CharacterUtils.getInstance(version)
+ ? CharacterUtils.getInstance()
: CharacterUtils.getJava4Instance();
this.minGram = minGram;
this.maxGram = maxGram;
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java Wed Jul 30 22:16:16 2014
@@ -81,10 +81,10 @@ public final class NGramTokenFilter exte
* @param maxGram the largest n-gram to generate
*/
public NGramTokenFilter(Version version, TokenStream input, int minGram, int maxGram) {
- super(new CodepointCountFilter(version, input, minGram, Integer.MAX_VALUE));
+ super(new CodepointCountFilter(input, minGram, Integer.MAX_VALUE));
this.version = version;
this.charUtils = version.onOrAfter(Version.LUCENE_4_4)
- ? CharacterUtils.getInstance(version)
+ ? CharacterUtils.getInstance()
: CharacterUtils.getJava4Instance();
if (minGram < 1) {
throw new IllegalArgumentException("minGram must be greater than zero");
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java Wed Jul 30 22:16:16 2014
@@ -121,7 +121,7 @@ public class NGramTokenizer extends Toke
throw new IllegalArgumentException("This class only works with Lucene 4.4+. To emulate the old (broken) behavior of NGramTokenizer, use Lucene43NGramTokenizer");
}
charUtils = version.onOrAfter(Version.LUCENE_4_4)
- ? CharacterUtils.getInstance(version)
+ ? CharacterUtils.getInstance()
: CharacterUtils.getJava4Instance();
if (minGram < 1) {
throw new IllegalArgumentException("minGram must be greater than zero");
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -28,13 +28,11 @@ import org.apache.lucene.analysis.miscel
import org.apache.lucene.analysis.snowball.SnowballFilter;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
-import org.apache.lucene.analysis.standard.StandardAnalyzer; // for javadoc
import org.apache.lucene.analysis.util.CharArrayMap;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.WordlistLoader;
import org.apache.lucene.util.CharsRef;
import org.apache.lucene.util.IOUtils;
-import org.apache.lucene.util.Version;
import java.io.IOException;
import java.io.Reader;
@@ -50,10 +48,8 @@ import java.nio.charset.StandardCharsets
* A default set of stopwords is used unless an alternative list is specified, but the
* exclusion list is empty by default.
* </p>
- *
- * <p><b>NOTE</b>: This class uses the same {@link Version}
- * dependent settings as {@link StandardAnalyzer}.</p>
*/
+// TODO: extend StopwordAnalyzerBase
public final class DutchAnalyzer extends Analyzer {
/** File containing default Dutch stopwords. */
@@ -73,14 +69,14 @@ public final class DutchAnalyzer extends
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
- DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), Version.LUCENE_CURRENT);
+ DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8));
} catch (IOException ex) {
// default set should always be present as it is part of the
// distribution (JAR)
throw new RuntimeException("Unable to load default stopword set");
}
- DEFAULT_STEM_DICT = new CharArrayMap<>(Version.LUCENE_CURRENT, 4, false);
+ DEFAULT_STEM_DICT = new CharArrayMap<>(4, false);
DEFAULT_STEM_DICT.put("fiets", "fiets"); //otherwise fiet
DEFAULT_STEM_DICT.put("bromfiets", "bromfiets"); //otherwise bromfiet
DEFAULT_STEM_DICT.put("ei", "eier");
@@ -100,29 +96,27 @@ public final class DutchAnalyzer extends
private CharArraySet excltable = CharArraySet.EMPTY_SET;
private final StemmerOverrideMap stemdict;
- private final Version matchVersion;
/**
* Builds an analyzer with the default stop words ({@link #getDefaultStopSet()})
* and a few default entries for the stem exclusion table.
*
*/
- public DutchAnalyzer(Version matchVersion) {
- this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET, CharArraySet.EMPTY_SET, DefaultSetHolder.DEFAULT_STEM_DICT);
+ public DutchAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET, CharArraySet.EMPTY_SET, DefaultSetHolder.DEFAULT_STEM_DICT);
}
- public DutchAnalyzer(Version matchVersion, CharArraySet stopwords){
- this(matchVersion, stopwords, CharArraySet.EMPTY_SET, DefaultSetHolder.DEFAULT_STEM_DICT);
+ public DutchAnalyzer(CharArraySet stopwords){
+ this(stopwords, CharArraySet.EMPTY_SET, DefaultSetHolder.DEFAULT_STEM_DICT);
}
- public DutchAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionTable){
- this(matchVersion, stopwords, stemExclusionTable, DefaultSetHolder.DEFAULT_STEM_DICT);
+ public DutchAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionTable){
+ this(stopwords, stemExclusionTable, DefaultSetHolder.DEFAULT_STEM_DICT);
}
- public DutchAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionTable, CharArrayMap<String> stemOverrideDict) {
- this.matchVersion = matchVersion;
- this.stoptable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stopwords));
- this.excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionTable));
+ public DutchAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionTable, CharArrayMap<String> stemOverrideDict) {
+ this.stoptable = CharArraySet.unmodifiableSet(CharArraySet.copy(stopwords));
+ this.excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionTable));
if (stemOverrideDict.isEmpty()) {
this.stemdict = null;
} else {
@@ -154,10 +148,10 @@ public final class DutchAnalyzer extends
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- final Tokenizer source = new StandardTokenizer(matchVersion);
- TokenStream result = new StandardFilter(matchVersion, source);
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stoptable);
+ final Tokenizer source = new StandardTokenizer();
+ TokenStream result = new StandardFilter(source);
+ result = new LowerCaseFilter(result);
+ result = new StopFilter(result, stoptable);
if (!excltable.isEmpty())
result = new SetKeywordMarkerFilter(result, excltable);
if (stemdict != null)
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/no/NorwegianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/no/NorwegianAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/no/NorwegianAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/no/NorwegianAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -34,7 +34,6 @@ import org.apache.lucene.analysis.util.C
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.analysis.util.WordlistLoader;
import org.apache.lucene.util.IOUtils;
-import org.apache.lucene.util.Version;
import org.tartarus.snowball.ext.NorwegianStemmer;
/**
@@ -64,7 +63,7 @@ public final class NorwegianAnalyzer ext
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
- DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), Version.LUCENE_CURRENT);
+ DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8));
} catch (IOException ex) {
// default set should always be present as it is part of the
// distribution (JAR)
@@ -76,18 +75,17 @@ public final class NorwegianAnalyzer ext
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
- public NorwegianAnalyzer(Version matchVersion) {
- this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
+ public NorwegianAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* Builds an analyzer with the given stop words.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public NorwegianAnalyzer(Version matchVersion, CharArraySet stopwords) {
- this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
+ public NorwegianAnalyzer(CharArraySet stopwords) {
+ this(stopwords, CharArraySet.EMPTY_SET);
}
/**
@@ -95,14 +93,12 @@ public final class NorwegianAnalyzer ext
* provided this analyzer will add a {@link SetKeywordMarkerFilter} before
* stemming.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public NorwegianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
- super(matchVersion, stopwords);
- this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
- matchVersion, stemExclusionSet));
+ public NorwegianAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
}
/**
@@ -119,10 +115,10 @@ public final class NorwegianAnalyzer ext
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- final Tokenizer source = new StandardTokenizer(matchVersion);
- TokenStream result = new StandardFilter(matchVersion, source);
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ final Tokenizer source = new StandardTokenizer();
+ TokenStream result = new StandardFilter(source);
+ result = new LowerCaseFilter(result);
+ result = new StopFilter(result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SnowballFilter(result, new NorwegianStemmer());
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -34,7 +34,6 @@ import org.apache.lucene.analysis.util.C
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.analysis.util.WordlistLoader;
import org.apache.lucene.util.IOUtils;
-import org.apache.lucene.util.Version;
/**
* {@link Analyzer} for Portuguese.
@@ -63,7 +62,7 @@ public final class PortugueseAnalyzer ex
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
- DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), Version.LUCENE_CURRENT);
+ DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8));
} catch (IOException ex) {
// default set should always be present as it is part of the
// distribution (JAR)
@@ -75,18 +74,17 @@ public final class PortugueseAnalyzer ex
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
- public PortugueseAnalyzer(Version matchVersion) {
- this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
+ public PortugueseAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* Builds an analyzer with the given stop words.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public PortugueseAnalyzer(Version matchVersion, CharArraySet stopwords) {
- this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
+ public PortugueseAnalyzer(CharArraySet stopwords) {
+ this(stopwords, CharArraySet.EMPTY_SET);
}
/**
@@ -94,14 +92,12 @@ public final class PortugueseAnalyzer ex
* provided this analyzer will add a {@link SetKeywordMarkerFilter} before
* stemming.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public PortugueseAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
- super(matchVersion, stopwords);
- this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
- matchVersion, stemExclusionSet));
+ public PortugueseAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
}
/**
@@ -118,10 +114,10 @@ public final class PortugueseAnalyzer ex
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- final Tokenizer source = new StandardTokenizer(matchVersion);
- TokenStream result = new StandardFilter(matchVersion, source);
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ final Tokenizer source = new StandardTokenizer();
+ TokenStream result = new StandardFilter(source);
+ result = new LowerCaseFilter(result);
+ result = new StopFilter(result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new PortugueseLightStemFilter(result);
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/RSLPStemmerBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/RSLPStemmerBase.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/RSLPStemmerBase.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/RSLPStemmerBase.java Wed Jul 30 22:16:16 2014
@@ -31,7 +31,6 @@ import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.lucene.analysis.util.CharArraySet;
-import org.apache.lucene.util.Version;
import static org.apache.lucene.analysis.util.StemmerUtil.*;
@@ -135,8 +134,7 @@ public abstract class RSLPStemmerBase {
if (!exceptions[i].endsWith(suffix))
throw new RuntimeException("useless exception '" + exceptions[i] + "' does not end with '" + suffix + "'");
}
- this.exceptions = new CharArraySet(Version.LUCENE_CURRENT,
- Arrays.asList(exceptions), false);
+ this.exceptions = new CharArraySet(Arrays.asList(exceptions), false);
}
@Override
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -31,7 +31,6 @@ import org.apache.lucene.index.TermsEnum
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.CharsRef;
import org.apache.lucene.util.UnicodeUtil;
-import org.apache.lucene.util.Version;
/**
* An {@link Analyzer} used primarily at query time to wrap another analyzer and provide a layer of protection
@@ -50,23 +49,20 @@ public final class QueryAutoStopWordAnal
//The default maximum percentage (40%) of index documents which
//can contain a term, after which the term is considered to be a stop word.
public static final float defaultMaxDocFreqPercent = 0.4f;
- private final Version matchVersion;
/**
* Creates a new QueryAutoStopWordAnalyzer with stopwords calculated for all
* indexed fields from terms with a document frequency percentage greater than
* {@link #defaultMaxDocFreqPercent}
*
- * @param matchVersion Version to be used in {@link StopFilter}
* @param delegate Analyzer whose TokenStream will be filtered
* @param indexReader IndexReader to identify the stopwords from
* @throws IOException Can be thrown while reading from the IndexReader
*/
public QueryAutoStopWordAnalyzer(
- Version matchVersion,
Analyzer delegate,
IndexReader indexReader) throws IOException {
- this(matchVersion, delegate, indexReader, defaultMaxDocFreqPercent);
+ this(delegate, indexReader, defaultMaxDocFreqPercent);
}
/**
@@ -74,18 +70,16 @@ public final class QueryAutoStopWordAnal
* indexed fields from terms with a document frequency greater than the given
* maxDocFreq
*
- * @param matchVersion Version to be used in {@link StopFilter}
* @param delegate Analyzer whose TokenStream will be filtered
* @param indexReader IndexReader to identify the stopwords from
* @param maxDocFreq Document frequency terms should be above in order to be stopwords
* @throws IOException Can be thrown while reading from the IndexReader
*/
public QueryAutoStopWordAnalyzer(
- Version matchVersion,
Analyzer delegate,
IndexReader indexReader,
int maxDocFreq) throws IOException {
- this(matchVersion, delegate, indexReader, MultiFields.getIndexedFields(indexReader), maxDocFreq);
+ this(delegate, indexReader, MultiFields.getIndexedFields(indexReader), maxDocFreq);
}
/**
@@ -93,7 +87,6 @@ public final class QueryAutoStopWordAnal
* indexed fields from terms with a document frequency percentage greater than
* the given maxPercentDocs
*
- * @param matchVersion Version to be used in {@link StopFilter}
* @param delegate Analyzer whose TokenStream will be filtered
* @param indexReader IndexReader to identify the stopwords from
* @param maxPercentDocs The maximum percentage (between 0.0 and 1.0) of index documents which
@@ -101,11 +94,10 @@ public final class QueryAutoStopWordAnal
* @throws IOException Can be thrown while reading from the IndexReader
*/
public QueryAutoStopWordAnalyzer(
- Version matchVersion,
Analyzer delegate,
IndexReader indexReader,
float maxPercentDocs) throws IOException {
- this(matchVersion, delegate, indexReader, MultiFields.getIndexedFields(indexReader), maxPercentDocs);
+ this(delegate, indexReader, MultiFields.getIndexedFields(indexReader), maxPercentDocs);
}
/**
@@ -113,7 +105,6 @@ public final class QueryAutoStopWordAnal
* given selection of fields from terms with a document frequency percentage
* greater than the given maxPercentDocs
*
- * @param matchVersion Version to be used in {@link StopFilter}
* @param delegate Analyzer whose TokenStream will be filtered
* @param indexReader IndexReader to identify the stopwords from
* @param fields Selection of fields to calculate stopwords for
@@ -122,12 +113,11 @@ public final class QueryAutoStopWordAnal
* @throws IOException Can be thrown while reading from the IndexReader
*/
public QueryAutoStopWordAnalyzer(
- Version matchVersion,
Analyzer delegate,
IndexReader indexReader,
Collection<String> fields,
float maxPercentDocs) throws IOException {
- this(matchVersion, delegate, indexReader, fields, (int) (indexReader.numDocs() * maxPercentDocs));
+ this(delegate, indexReader, fields, (int) (indexReader.numDocs() * maxPercentDocs));
}
/**
@@ -135,7 +125,6 @@ public final class QueryAutoStopWordAnal
* given selection of fields from terms with a document frequency greater than
* the given maxDocFreq
*
- * @param matchVersion Version to be used in {@link StopFilter}
* @param delegate Analyzer whose TokenStream will be filtered
* @param indexReader IndexReader to identify the stopwords from
* @param fields Selection of fields to calculate stopwords for
@@ -143,13 +132,11 @@ public final class QueryAutoStopWordAnal
* @throws IOException Can be thrown while reading from the IndexReader
*/
public QueryAutoStopWordAnalyzer(
- Version matchVersion,
Analyzer delegate,
IndexReader indexReader,
Collection<String> fields,
int maxDocFreq) throws IOException {
super(delegate.getReuseStrategy());
- this.matchVersion = matchVersion;
this.delegate = delegate;
for (String field : fields) {
@@ -181,8 +168,8 @@ public final class QueryAutoStopWordAnal
if (stopWords == null) {
return components;
}
- StopFilter stopFilter = new StopFilter(matchVersion, components.getTokenStream(),
- new CharArraySet(matchVersion, stopWords, false));
+ StopFilter stopFilter = new StopFilter(components.getTokenStream(),
+ new CharArraySet(stopWords, false));
return new TokenStreamComponents(components.getTokenizer(), stopFilter);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java Wed Jul 30 22:16:16 2014
@@ -20,7 +20,6 @@ package org.apache.lucene.analysis.rever
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
-import org.apache.lucene.util.Version;
import java.io.IOException;
@@ -36,7 +35,6 @@ public final class ReverseStringFilter e
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final char marker;
- private final Version matchVersion;
private static final char NOMARKER = '\uFFFF';
/**
@@ -66,11 +64,10 @@ public final class ReverseStringFilter e
* The reversed tokens will not be marked.
* </p>
*
- * @param matchVersion Lucene compatibility version
* @param in {@link TokenStream} to filter
*/
- public ReverseStringFilter(Version matchVersion, TokenStream in) {
- this(matchVersion, in, NOMARKER);
+ public ReverseStringFilter(TokenStream in) {
+ this(in, NOMARKER);
}
/**
@@ -81,13 +78,11 @@ public final class ReverseStringFilter e
* character.
* </p>
*
- * @param matchVersion compatibility version
* @param in {@link TokenStream} to filter
* @param marker A character used to mark reversed tokens
*/
- public ReverseStringFilter(Version matchVersion, TokenStream in, char marker) {
+ public ReverseStringFilter(TokenStream in, char marker) {
super(in);
- this.matchVersion = matchVersion;
this.marker = marker;
}
@@ -100,7 +95,7 @@ public final class ReverseStringFilter e
termAtt.resizeBuffer(len);
termAtt.buffer()[len - 1] = marker;
}
- reverse( matchVersion, termAtt.buffer(), 0, len );
+ reverse( termAtt.buffer(), 0, len );
termAtt.setLength(len);
return true;
} else {
@@ -111,48 +106,43 @@ public final class ReverseStringFilter e
/**
* Reverses the given input string
*
- * @param matchVersion compatibility version
* @param input the string to reverse
* @return the given input string in reversed order
*/
- public static String reverse( Version matchVersion, final String input ){
+ public static String reverse(final String input ){
final char[] charInput = input.toCharArray();
- reverse( matchVersion, charInput, 0, charInput.length );
+ reverse( charInput, 0, charInput.length );
return new String( charInput );
}
/**
* Reverses the given input buffer in-place
- * @param matchVersion compatibility version
* @param buffer the input char array to reverse
*/
- public static void reverse(Version matchVersion, final char[] buffer) {
- reverse(matchVersion, buffer, 0, buffer.length);
+ public static void reverse(final char[] buffer) {
+ reverse(buffer, 0, buffer.length);
}
/**
* Partially reverses the given input buffer in-place from offset 0
* up to the given length.
- * @param matchVersion compatibility version
* @param buffer the input char array to reverse
* @param len the length in the buffer up to where the
* buffer should be reversed
*/
- public static void reverse(Version matchVersion, final char[] buffer,
- final int len) {
- reverse( matchVersion, buffer, 0, len );
+ public static void reverse(final char[] buffer, final int len) {
+ reverse( buffer, 0, len );
}
/**
* Partially reverses the given input buffer in-place from the given offset
* up to the given length.
- * @param matchVersion compatibility version
* @param buffer the input char array to reverse
* @param start the offset from where to reverse the buffer
* @param len the length in the buffer up to where the
* buffer should be reversed
*/
- public static void reverse(Version matchVersion, final char[] buffer,
+ public static void reverse(final char[] buffer,
final int start, final int len) {
/* modified version of Apache Harmony AbstractStringBuilder reverse0() */
if (len < 2)
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilterFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilterFactory.java Wed Jul 30 22:16:16 2014
@@ -40,7 +40,6 @@ public class ReverseStringFilterFactory
/** Creates a new ReverseStringFilterFactory */
public ReverseStringFilterFactory(Map<String,String> args) {
super(args);
- assureMatchVersion();
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
}
@@ -48,7 +47,7 @@ public class ReverseStringFilterFactory
@Override
public ReverseStringFilter create(TokenStream in) {
- return new ReverseStringFilter(luceneMatchVersion,in);
+ return new ReverseStringFilter(in);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ro/RomanianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ro/RomanianAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ro/RomanianAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ro/RomanianAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -78,18 +78,17 @@ public final class RomanianAnalyzer exte
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
- public RomanianAnalyzer(Version matchVersion) {
- this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
+ public RomanianAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* Builds an analyzer with the given stop words.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public RomanianAnalyzer(Version matchVersion, CharArraySet stopwords) {
- this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
+ public RomanianAnalyzer(CharArraySet stopwords) {
+ this(stopwords, CharArraySet.EMPTY_SET);
}
/**
@@ -97,14 +96,12 @@ public final class RomanianAnalyzer exte
* provided this analyzer will add a {@link SetKeywordMarkerFilter} before
* stemming.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public RomanianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
- super(matchVersion, stopwords);
- this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
- matchVersion, stemExclusionSet));
+ public RomanianAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
}
/**
@@ -121,10 +118,10 @@ public final class RomanianAnalyzer exte
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- final Tokenizer source = new StandardTokenizer(matchVersion);
- TokenStream result = new StandardFilter(matchVersion, source);
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ final Tokenizer source = new StandardTokenizer();
+ TokenStream result = new StandardFilter(source);
+ result = new LowerCaseFilter(result);
+ result = new StopFilter(result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SnowballFilter(result, new RomanianStemmer());
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -54,7 +54,7 @@ public final class RussianAnalyzer exten
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
- DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), Version.LUCENE_CURRENT);
+ DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8));
} catch (IOException ex) {
// default set should always be present as it is part of the
// distribution (JAR)
@@ -74,34 +74,30 @@ public final class RussianAnalyzer exten
return DefaultSetHolder.DEFAULT_STOP_SET;
}
- public RussianAnalyzer(Version matchVersion) {
- this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
+ public RussianAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* Builds an analyzer with the given stop words
*
- * @param matchVersion
- * lucene compatibility version
* @param stopwords
* a stopword set
*/
- public RussianAnalyzer(Version matchVersion, CharArraySet stopwords){
- this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
+ public RussianAnalyzer(CharArraySet stopwords) {
+ this(stopwords, CharArraySet.EMPTY_SET);
}
/**
* Builds an analyzer with the given stop words
*
- * @param matchVersion
- * lucene compatibility version
* @param stopwords
* a stopword set
* @param stemExclusionSet a set of words not to be stemmed
*/
- public RussianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet){
- super(matchVersion, stopwords);
- this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet));
+ public RussianAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
}
/**
@@ -117,10 +113,10 @@ public final class RussianAnalyzer exten
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- final Tokenizer source = new StandardTokenizer(matchVersion);
- TokenStream result = new StandardFilter(matchVersion, source);
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ final Tokenizer source = new StandardTokenizer();
+ TokenStream result = new StandardFilter(source);
+ result = new LowerCaseFilter(result);
+ result = new StopFilter(result, stopwords);
if (!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SnowballFilter(result, new org.tartarus.snowball.ext.RussianStemmer());
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapper.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapper.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapper.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapper.java Wed Jul 30 22:16:16 2014
@@ -20,7 +20,6 @@ package org.apache.lucene.analysis.shing
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.AnalyzerWrapper;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
-import org.apache.lucene.util.Version;
/**
* A ShingleAnalyzerWrapper wraps a {@link ShingleFilter} around another {@link Analyzer}.
@@ -101,15 +100,15 @@ public final class ShingleAnalyzerWrappe
/**
* Wraps {@link StandardAnalyzer}.
*/
- public ShingleAnalyzerWrapper(Version matchVersion) {
- this(matchVersion, ShingleFilter.DEFAULT_MIN_SHINGLE_SIZE, ShingleFilter.DEFAULT_MAX_SHINGLE_SIZE);
+ public ShingleAnalyzerWrapper() {
+ this(ShingleFilter.DEFAULT_MIN_SHINGLE_SIZE, ShingleFilter.DEFAULT_MAX_SHINGLE_SIZE);
}
/**
* Wraps {@link StandardAnalyzer}.
*/
- public ShingleAnalyzerWrapper(Version matchVersion, int minShingleSize, int maxShingleSize) {
- this(new StandardAnalyzer(matchVersion), minShingleSize, maxShingleSize);
+ public ShingleAnalyzerWrapper(int minShingleSize, int maxShingleSize) {
+ this(new StandardAnalyzer(), minShingleSize, maxShingleSize);
}
/**
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -17,16 +17,14 @@ package org.apache.lucene.analysis.stand
* limitations under the License.
*/
-import org.apache.lucene.analysis.*;
+import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.analysis.util.WordlistLoader;
-import org.apache.lucene.util.Version;
-import java.io.File;
import java.io.IOException;
import java.io.Reader;
@@ -34,18 +32,6 @@ import java.io.Reader;
* Filters {@link ClassicTokenizer} with {@link ClassicFilter}, {@link
* LowerCaseFilter} and {@link StopFilter}, using a list of
* English stop words.
- *
- * <a name="version"/>
- * <p>You must specify the required {@link Version}
- * compatibility when creating ClassicAnalyzer:
- * <ul>
- * <li> As of 3.1, StopFilter correctly handles Unicode 4.0
- * supplementary characters in stopwords
- * <li> As of 2.9, StopFilter preserves position
- * increments
- * <li> As of 2.4, Tokens incorrectly identified as acronyms
- * are corrected (see <a href="https://issues.apache.org/jira/browse/LUCENE-1068">LUCENE-1068</a>)
- * </ul>
*
* ClassicAnalyzer was named StandardAnalyzer in Lucene versions prior to 3.1.
* As of 3.1, {@link StandardAnalyzer} implements Unicode text segmentation,
@@ -63,29 +49,23 @@ public final class ClassicAnalyzer exten
public static final CharArraySet STOP_WORDS_SET = StopAnalyzer.ENGLISH_STOP_WORDS_SET;
/** Builds an analyzer with the given stop words.
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
* @param stopWords stop words */
- public ClassicAnalyzer(Version matchVersion, CharArraySet stopWords) {
- super(matchVersion, stopWords);
+ public ClassicAnalyzer(CharArraySet stopWords) {
+ super(stopWords);
}
/** Builds an analyzer with the default stop words ({@link
* #STOP_WORDS_SET}).
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
*/
- public ClassicAnalyzer(Version matchVersion) {
- this(matchVersion, STOP_WORDS_SET);
+ public ClassicAnalyzer() {
+ this(STOP_WORDS_SET);
}
/** Builds an analyzer with the stop words from the given reader.
- * @see WordlistLoader#getWordSet(Reader, Version)
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
+ * @see WordlistLoader#getWordSet(Reader)
* @param stopwords Reader to read stop words from */
- public ClassicAnalyzer(Version matchVersion, Reader stopwords) throws IOException {
- this(matchVersion, loadStopwordSet(stopwords, matchVersion));
+ public ClassicAnalyzer(Reader stopwords) throws IOException {
+ this(loadStopwordSet(stopwords));
}
/**
@@ -107,11 +87,11 @@ public final class ClassicAnalyzer exten
@Override
protected TokenStreamComponents createComponents(final String fieldName) {
- final ClassicTokenizer src = new ClassicTokenizer(matchVersion);
+ final ClassicTokenizer src = new ClassicTokenizer();
src.setMaxTokenLength(maxTokenLength);
TokenStream tok = new ClassicFilter(src);
- tok = new LowerCaseFilter(matchVersion, tok);
- tok = new StopFilter(matchVersion, tok, stopwords);
+ tok = new LowerCaseFilter(tok);
+ tok = new StopFilter(tok, stopwords);
return new TokenStreamComponents(src, tok) {
@Override
protected void setReader(final Reader reader) throws IOException {
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizer.java Wed Jul 30 22:16:16 2014
@@ -18,7 +18,6 @@
package org.apache.lucene.analysis.standard;
import java.io.IOException;
-import java.io.Reader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
@@ -26,8 +25,6 @@ import org.apache.lucene.analysis.tokena
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.util.AttributeFactory;
-import org.apache.lucene.util.AttributeSource;
-import org.apache.lucene.util.Version;
/** A grammar-based tokenizer constructed with JFlex
*
@@ -102,19 +99,19 @@ public final class ClassicTokenizer exte
*
* See http://issues.apache.org/jira/browse/LUCENE-1068
*/
- public ClassicTokenizer(Version matchVersion) {
- init(matchVersion);
+ public ClassicTokenizer() {
+ init();
}
/**
* Creates a new ClassicTokenizer with a given {@link org.apache.lucene.util.AttributeFactory}
*/
- public ClassicTokenizer(Version matchVersion, AttributeFactory factory) {
+ public ClassicTokenizer(AttributeFactory factory) {
super(factory);
- init(matchVersion);
+ init();
}
- private void init(Version matchVersion) {
+ private void init() {
this.scanner = new ClassicTokenizerImpl(input);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizerFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizerFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizerFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizerFactory.java Wed Jul 30 22:16:16 2014
@@ -37,7 +37,6 @@ public class ClassicTokenizerFactory ext
/** Creates a new ClassicTokenizerFactory */
public ClassicTokenizerFactory(Map<String,String> args) {
super(args);
- assureMatchVersion();
maxTokenLength = getInt(args, "maxTokenLength", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
@@ -46,7 +45,7 @@ public class ClassicTokenizerFactory ext
@Override
public ClassicTokenizer create(AttributeFactory factory) {
- ClassicTokenizer tokenizer = new ClassicTokenizer(luceneMatchVersion, factory);
+ ClassicTokenizer tokenizer = new ClassicTokenizer(factory);
tokenizer.setMaxTokenLength(maxTokenLength);
return tokenizer;
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -17,16 +17,14 @@ package org.apache.lucene.analysis.stand
* limitations under the License.
*/
-import org.apache.lucene.analysis.*;
+import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.analysis.util.WordlistLoader;
-import org.apache.lucene.util.Version;
-import java.io.File;
import java.io.IOException;
import java.io.Reader;
@@ -34,26 +32,9 @@ import java.io.Reader;
* Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
* LowerCaseFilter} and {@link StopFilter}, using a list of
* English stop words.
- *
- * <a name="version"/>
- * <p>You must specify the required {@link Version}
- * compatibility when creating StandardAnalyzer:
- * <ul>
- * <li> As of 3.4, Hiragana and Han characters are no longer wrongly split
- * from their combining characters. If you use a previous version number,
- * you get the exact broken behavior for backwards compatibility.
- * <li> As of 3.1, StandardTokenizer implements Unicode text segmentation,
- * and StopFilter correctly handles Unicode 4.0 supplementary characters
- * in stopwords. {@link ClassicTokenizer} and {@link ClassicAnalyzer}
- * are the pre-3.1 implementations of StandardTokenizer and
- * StandardAnalyzer.
- * <li> As of 2.9, StopFilter preserves position increments
- * <li> As of 2.4, Tokens incorrectly identified as acronyms
- * are corrected (see <a href="https://issues.apache.org/jira/browse/LUCENE-1068">LUCENE-1068</a>)
- * </ul>
*/
public final class StandardAnalyzer extends StopwordAnalyzerBase {
-
+
/** Default maximum allowed token length */
public static final int DEFAULT_MAX_TOKEN_LENGTH = 255;
@@ -64,29 +45,22 @@ public final class StandardAnalyzer exte
public static final CharArraySet STOP_WORDS_SET = StopAnalyzer.ENGLISH_STOP_WORDS_SET;
/** Builds an analyzer with the given stop words.
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
* @param stopWords stop words */
- public StandardAnalyzer(Version matchVersion, CharArraySet stopWords) {
- super(matchVersion, stopWords);
+ public StandardAnalyzer(CharArraySet stopWords) {
+ super(stopWords);
}
- /** Builds an analyzer with the default stop words ({@link
- * #STOP_WORDS_SET}).
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
+ /** Builds an analyzer with the default stop words ({@link #STOP_WORDS_SET}).
*/
- public StandardAnalyzer(Version matchVersion) {
- this(matchVersion, STOP_WORDS_SET);
+ public StandardAnalyzer() {
+ this(STOP_WORDS_SET);
}
/** Builds an analyzer with the stop words from the given reader.
- * @see WordlistLoader#getWordSet(Reader, Version)
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
+ * @see WordlistLoader#getWordSet(Reader)
* @param stopwords Reader to read stop words from */
- public StandardAnalyzer(Version matchVersion, Reader stopwords) throws IOException {
- this(matchVersion, loadStopwordSet(stopwords, matchVersion));
+ public StandardAnalyzer(Reader stopwords) throws IOException {
+ this(loadStopwordSet(stopwords));
}
/**
@@ -108,11 +82,11 @@ public final class StandardAnalyzer exte
@Override
protected TokenStreamComponents createComponents(final String fieldName) {
- final StandardTokenizer src = new StandardTokenizer(matchVersion);
+ final StandardTokenizer src = new StandardTokenizer();
src.setMaxTokenLength(maxTokenLength);
- TokenStream tok = new StandardFilter(matchVersion, src);
- tok = new LowerCaseFilter(matchVersion, tok);
- tok = new StopFilter(matchVersion, tok, stopwords);
+ TokenStream tok = new StandardFilter(src);
+ tok = new LowerCaseFilter(tok);
+ tok = new StopFilter(tok, stopwords);
return new TokenStreamComponents(src, tok) {
@Override
protected void setReader(final Reader reader) throws IOException {
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilter.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilter.java Wed Jul 30 22:16:16 2014
@@ -21,14 +21,13 @@ import java.io.IOException;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.util.Version;
/**
* Normalizes tokens extracted with {@link StandardTokenizer}.
*/
public class StandardFilter extends TokenFilter {
- public StandardFilter(Version matchVersion, TokenStream in) {
+ public StandardFilter(TokenStream in) {
super(in);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilterFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilterFactory.java Wed Jul 30 22:16:16 2014
@@ -38,7 +38,6 @@ public class StandardFilterFactory exten
/** Creates a new StandardFilterFactory */
public StandardFilterFactory(Map<String,String> args) {
super(args);
- assureMatchVersion();
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
}
@@ -46,6 +45,6 @@ public class StandardFilterFactory exten
@Override
public StandardFilter create(TokenStream input) {
- return new StandardFilter(luceneMatchVersion, input);
+ return new StandardFilter(input);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizer.java Wed Jul 30 22:16:16 2014
@@ -18,7 +18,6 @@
package org.apache.lucene.analysis.standard;
import java.io.IOException;
-import java.io.Reader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
@@ -26,8 +25,6 @@ import org.apache.lucene.analysis.tokena
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.util.AttributeFactory;
-import org.apache.lucene.util.AttributeSource;
-import org.apache.lucene.util.Version;
/** A grammar-based tokenizer constructed with JFlex.
* <p>
@@ -116,19 +113,19 @@ public final class StandardTokenizer ext
* See http://issues.apache.org/jira/browse/LUCENE-1068
*/
- public StandardTokenizer(Version matchVersion) {
- init(matchVersion);
+ public StandardTokenizer() {
+ init();
}
/**
* Creates a new StandardTokenizer with a given {@link org.apache.lucene.util.AttributeFactory}
*/
- public StandardTokenizer(Version matchVersion, AttributeFactory factory) {
+ public StandardTokenizer(AttributeFactory factory) {
super(factory);
- init(matchVersion);
+ init();
}
- private void init(Version matchVersion) {
+ private void init() {
this.scanner = new StandardTokenizerImpl(input);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizerFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizerFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizerFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizerFactory.java Wed Jul 30 22:16:16 2014
@@ -37,7 +37,6 @@ public class StandardTokenizerFactory ex
/** Creates a new StandardTokenizerFactory */
public StandardTokenizerFactory(Map<String,String> args) {
super(args);
- assureMatchVersion();
maxTokenLength = getInt(args, "maxTokenLength", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
@@ -46,7 +45,7 @@ public class StandardTokenizerFactory ex
@Override
public StandardTokenizer create(AttributeFactory factory) {
- StandardTokenizer tokenizer = new StandardTokenizer(luceneMatchVersion, factory);
+ StandardTokenizer tokenizer = new StandardTokenizer(factory);
tokenizer.setMaxTokenLength(maxTokenLength);
return tokenizer;
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -34,15 +34,9 @@ import java.io.Reader;
* {@link org.apache.lucene.analysis.core.LowerCaseFilter} and
* {@link org.apache.lucene.analysis.core.StopFilter}, using a list of
* English stop words.
- *
- * <a name="version"/>
- * <p>
- * You must specify the required {@link org.apache.lucene.util.Version}
- * compatibility when creating UAX29URLEmailAnalyzer
- * </p>
*/
public final class UAX29URLEmailAnalyzer extends StopwordAnalyzerBase {
-
+
/** Default maximum allowed token length */
public static final int DEFAULT_MAX_TOKEN_LENGTH = StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH;
@@ -53,29 +47,23 @@ public final class UAX29URLEmailAnalyzer
public static final CharArraySet STOP_WORDS_SET = StopAnalyzer.ENGLISH_STOP_WORDS_SET;
/** Builds an analyzer with the given stop words.
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
* @param stopWords stop words */
- public UAX29URLEmailAnalyzer(Version matchVersion, CharArraySet stopWords) {
- super(matchVersion, stopWords);
+ public UAX29URLEmailAnalyzer(CharArraySet stopWords) {
+ super(stopWords);
}
/** Builds an analyzer with the default stop words ({@link
* #STOP_WORDS_SET}).
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
*/
- public UAX29URLEmailAnalyzer(Version matchVersion) {
- this(matchVersion, STOP_WORDS_SET);
+ public UAX29URLEmailAnalyzer() {
+ this(STOP_WORDS_SET);
}
/** Builds an analyzer with the stop words from the given reader.
- * @see org.apache.lucene.analysis.util.WordlistLoader#getWordSet(java.io.Reader, org.apache.lucene.util.Version)
- * @param matchVersion Lucene version to match See {@link
- * <a href="#version">above</a>}
+ * @see org.apache.lucene.analysis.util.WordlistLoader#getWordSet(java.io.Reader)
* @param stopwords Reader to read stop words from */
- public UAX29URLEmailAnalyzer(Version matchVersion, Reader stopwords) throws IOException {
- this(matchVersion, loadStopwordSet(stopwords, matchVersion));
+ public UAX29URLEmailAnalyzer(Reader stopwords) throws IOException {
+ this(loadStopwordSet(stopwords));
}
/**
@@ -97,11 +85,11 @@ public final class UAX29URLEmailAnalyzer
@Override
protected TokenStreamComponents createComponents(final String fieldName) {
- final UAX29URLEmailTokenizer src = new UAX29URLEmailTokenizer(matchVersion);
+ final UAX29URLEmailTokenizer src = new UAX29URLEmailTokenizer();
src.setMaxTokenLength(maxTokenLength);
- TokenStream tok = new StandardFilter(matchVersion, src);
- tok = new LowerCaseFilter(matchVersion, tok);
- tok = new StopFilter(matchVersion, tok, stopwords);
+ TokenStream tok = new StandardFilter(src);
+ tok = new LowerCaseFilter(tok);
+ tok = new StopFilter(tok, stopwords);
return new TokenStreamComponents(src, tok) {
@Override
protected void setReader(final Reader reader) throws IOException {
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizer.java Wed Jul 30 22:16:16 2014
@@ -18,9 +18,6 @@ package org.apache.lucene.analysis.stand
*/
import java.io.IOException;
-import java.io.InputStream;
-import java.io.InputStreamReader;
-import java.io.Reader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
@@ -28,8 +25,6 @@ import org.apache.lucene.analysis.tokena
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.util.AttributeFactory;
-import org.apache.lucene.util.AttributeSource;
-import org.apache.lucene.util.Version;
/**
* This class implements Word Break rules from the Unicode Text Segmentation
@@ -100,19 +95,19 @@ public final class UAX29URLEmailTokenize
* the <code>input</code> to the newly created JFlex scanner.
*/
- public UAX29URLEmailTokenizer(Version matchVersion) {
- this.scanner = getScannerFor(matchVersion);
+ public UAX29URLEmailTokenizer() {
+ this.scanner = getScanner();
}
/**
* Creates a new UAX29URLEmailTokenizer with a given {@link AttributeFactory}
*/
- public UAX29URLEmailTokenizer(Version matchVersion, AttributeFactory factory) {
+ public UAX29URLEmailTokenizer(AttributeFactory factory) {
super(factory);
- this.scanner = getScannerFor(matchVersion);
+ this.scanner = getScanner();
}
- private StandardTokenizerInterface getScannerFor(Version matchVersion) {
+ private StandardTokenizerInterface getScanner() {
return new UAX29URLEmailTokenizerImpl(input);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerFactory.java Wed Jul 30 22:16:16 2014
@@ -38,7 +38,6 @@ public class UAX29URLEmailTokenizerFacto
/** Creates a new UAX29URLEmailTokenizerFactory */
public UAX29URLEmailTokenizerFactory(Map<String,String> args) {
super(args);
- assureMatchVersion();
maxTokenLength = getInt(args, "maxTokenLength", StandardAnalyzer.DEFAULT_MAX_TOKEN_LENGTH);
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
@@ -47,7 +46,7 @@ public class UAX29URLEmailTokenizerFacto
@Override
public UAX29URLEmailTokenizer create(AttributeFactory factory) {
- UAX29URLEmailTokenizer tokenizer = new UAX29URLEmailTokenizer(luceneMatchVersion, factory);
+ UAX29URLEmailTokenizer tokenizer = new UAX29URLEmailTokenizer(factory);
tokenizer.setMaxTokenLength(maxTokenLength);
return tokenizer;
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/sv/SwedishAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/sv/SwedishAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/sv/SwedishAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/sv/SwedishAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -34,7 +34,6 @@ import org.apache.lucene.analysis.util.C
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.analysis.util.WordlistLoader;
import org.apache.lucene.util.IOUtils;
-import org.apache.lucene.util.Version;
import org.tartarus.snowball.ext.SwedishStemmer;
/**
@@ -64,7 +63,7 @@ public final class SwedishAnalyzer exten
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
- DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), Version.LUCENE_CURRENT);
+ DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8));
} catch (IOException ex) {
// default set should always be present as it is part of the
// distribution (JAR)
@@ -76,18 +75,17 @@ public final class SwedishAnalyzer exten
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
- public SwedishAnalyzer(Version matchVersion) {
- this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
+ public SwedishAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
}
/**
* Builds an analyzer with the given stop words.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public SwedishAnalyzer(Version matchVersion, CharArraySet stopwords) {
- this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
+ public SwedishAnalyzer(CharArraySet stopwords) {
+ this(stopwords, CharArraySet.EMPTY_SET);
}
/**
@@ -95,14 +93,12 @@ public final class SwedishAnalyzer exten
* provided this analyzer will add a {@link SetKeywordMarkerFilter} before
* stemming.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public SwedishAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
- super(matchVersion, stopwords);
- this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
- matchVersion, stemExclusionSet));
+ public SwedishAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
}
/**
@@ -119,10 +115,10 @@ public final class SwedishAnalyzer exten
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- final Tokenizer source = new StandardTokenizer(matchVersion);
- TokenStream result = new StandardFilter(matchVersion, source);
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ final Tokenizer source = new StandardTokenizer();
+ TokenStream result = new StandardFilter(source);
+ result = new LowerCaseFilter(result);
+ result = new StopFilter(result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SnowballFilter(result, new SwedishStemmer());
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilterFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilterFactory.java Wed Jul 30 22:16:16 2014
@@ -134,8 +134,8 @@ public class SynonymFilterFactory extend
analyzer = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer(Version.LUCENE_CURRENT) : factory.create();
- TokenStream stream = ignoreCase ? new LowerCaseFilter(Version.LUCENE_CURRENT, tokenizer) : tokenizer;
+ Tokenizer tokenizer = factory == null ? new WhitespaceTokenizer() : factory.create();
+ TokenStream stream = ignoreCase ? new LowerCaseFilter(tokenizer) : tokenizer;
return new TokenStreamComponents(tokenizer, stream);
}
};
@@ -202,7 +202,12 @@ public class SynonymFilterFactory extend
private Analyzer loadAnalyzer(ResourceLoader loader, String cname) throws IOException {
Class<? extends Analyzer> clazz = loader.findClass(cname, Analyzer.class);
try {
- Analyzer analyzer = clazz.getConstructor(Version.class).newInstance(Version.LUCENE_CURRENT);
+ Analyzer analyzer = null;
+ try {
+ analyzer = clazz.getConstructor().newInstance();
+ } catch (NoSuchMethodException e) {
+ analyzer = clazz.getConstructor(Version.class).newInstance(Version.LUCENE_CURRENT);
+ }
if (analyzer instanceof ResourceLoaderAware) {
((ResourceLoaderAware) analyzer).inform(loader);
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -23,7 +23,6 @@ import org.apache.lucene.analysis.Analyz
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
-import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
@@ -35,6 +34,7 @@ import org.apache.lucene.util.Version;
* {@link Analyzer} for Thai language. It uses {@link java.text.BreakIterator} to break words.
*/
public final class ThaiAnalyzer extends StopwordAnalyzerBase {
+ private final Version matchVersion;
/** File containing default Thai stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
@@ -87,7 +87,8 @@ public final class ThaiAnalyzer extends
* @param stopwords a stopword set
*/
public ThaiAnalyzer(Version matchVersion, CharArraySet stopwords) {
- super(matchVersion, stopwords);
+ super(stopwords);
+ this.matchVersion = matchVersion;
}
/**
@@ -104,15 +105,15 @@ public final class ThaiAnalyzer extends
protected TokenStreamComponents createComponents(String fieldName) {
if (matchVersion.onOrAfter(Version.LUCENE_4_8)) {
final Tokenizer source = new ThaiTokenizer();
- TokenStream result = new LowerCaseFilter(matchVersion, source);
- result = new StopFilter(matchVersion, result, stopwords);
+ TokenStream result = new LowerCaseFilter(source);
+ result = new StopFilter(result, stopwords);
return new TokenStreamComponents(source, result);
} else {
- final Tokenizer source = new StandardTokenizer(matchVersion);
- TokenStream result = new StandardFilter(matchVersion, source);
- result = new LowerCaseFilter(matchVersion, result);
- result = new ThaiWordFilter(matchVersion, result);
- return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords));
+ final Tokenizer source = new StandardTokenizer();
+ TokenStream result = new StandardFilter(source);
+ result = new LowerCaseFilter(result);
+ result = new ThaiWordFilter(result);
+ return new TokenStreamComponents(source, new StopFilter(result, stopwords));
}
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java Wed Jul 30 22:16:16 2014
@@ -28,7 +28,6 @@ import org.apache.lucene.analysis.tokena
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.analysis.util.CharArrayIterator;
import org.apache.lucene.util.AttributeSource;
-import org.apache.lucene.util.Version;
/**
* {@link TokenFilter} that use {@link java.text.BreakIterator} to break each
@@ -61,7 +60,7 @@ public final class ThaiWordFilter extend
private boolean hasIllegalOffsets = false; // only if the length changed before this filter
/** Creates a new ThaiWordFilter with the specified match version. */
- public ThaiWordFilter(Version matchVersion, TokenStream input) {
+ public ThaiWordFilter(TokenStream input) {
super(input);
if (!DBBI_AVAILABLE)
throw new UnsupportedOperationException("This JRE does not have support for Thai segmentation");
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilterFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilterFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilterFactory.java Wed Jul 30 22:16:16 2014
@@ -41,7 +41,6 @@ public class ThaiWordFilterFactory exten
/** Creates a new ThaiWordFilterFactory */
public ThaiWordFilterFactory(Map<String,String> args) {
super(args);
- assureMatchVersion();
if (!args.isEmpty()) {
throw new IllegalArgumentException("Unknown parameters: " + args);
}
@@ -49,7 +48,7 @@ public class ThaiWordFilterFactory exten
@Override
public ThaiWordFilter create(TokenStream input) {
- return new ThaiWordFilter(luceneMatchVersion, input);
+ return new ThaiWordFilter(input);
}
}
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishAnalyzer.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishAnalyzer.java Wed Jul 30 22:16:16 2014
@@ -38,6 +38,7 @@ import org.tartarus.snowball.ext.Turkish
*/
public final class TurkishAnalyzer extends StopwordAnalyzerBase {
private final CharArraySet stemExclusionSet;
+ private final Version matchVersion;
/** File containing default Turkish stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
@@ -101,9 +102,9 @@ public final class TurkishAnalyzer exten
* @param stemExclusionSet a set of terms not to be stemmed
*/
public TurkishAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
- super(matchVersion, stopwords);
- this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
- matchVersion, stemExclusionSet));
+ super(stopwords);
+ this.matchVersion = matchVersion;
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
}
/**
@@ -120,12 +121,12 @@ public final class TurkishAnalyzer exten
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
- final Tokenizer source = new StandardTokenizer(matchVersion);
- TokenStream result = new StandardFilter(matchVersion, source);
+ final Tokenizer source = new StandardTokenizer();
+ TokenStream result = new StandardFilter(source);
if(matchVersion.onOrAfter(Version.LUCENE_4_8))
result = new ApostropheFilter(result);
result = new TurkishLowerCaseFilter(result);
- result = new StopFilter(matchVersion, result, stopwords);
+ result = new StopFilter(result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SnowballFilter(result, new TurkishStemmer());
Modified: lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AbstractAnalysisFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AbstractAnalysisFactory.java?rev=1614778&r1=1614777&r2=1614778&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AbstractAnalysisFactory.java (original)
+++ lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/AbstractAnalysisFactory.java Wed Jul 30 22:16:16 2014
@@ -238,12 +238,10 @@ public abstract class AbstractAnalysisFa
if (files.size() > 0) {
// default stopwords list has 35 or so words, but maybe don't make it that
// big to start
- words = new CharArraySet(luceneMatchVersion,
- files.size() * 10, ignoreCase);
+ words = new CharArraySet(files.size() * 10, ignoreCase);
for (String file : files) {
List<String> wlist = getLines(loader, file.trim());
- words.addAll(StopFilter.makeStopSet(luceneMatchVersion, wlist,
- ignoreCase));
+ words.addAll(StopFilter.makeStopSet(wlist, ignoreCase));
}
}
return words;
@@ -266,8 +264,7 @@ public abstract class AbstractAnalysisFa
if (files.size() > 0) {
// default stopwords list has 35 or so words, but maybe don't make it that
// big to start
- words = new CharArraySet(luceneMatchVersion,
- files.size() * 10, ignoreCase);
+ words = new CharArraySet(files.size() * 10, ignoreCase);
for (String file : files) {
InputStream stream = null;
Reader reader = null;