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 2012/02/09 20:59:53 UTC
svn commit: r1242497 [1/3] - in /lucene/dev/trunk: lucene/ lucene/contrib/
modules/analysis/
modules/analysis/common/src/java/org/apache/lucene/analysis/ar/
modules/analysis/common/src/java/org/apache/lucene/analysis/bg/
modules/analysis/common/src/jav...
Author: rmuir
Date: Thu Feb 9 19:59:50 2012
New Revision: 1242497
URL: http://svn.apache.org/viewvc?rev=1242497&view=rev
Log:
LUCENE-3765: Trappy behavior with StopFilter/ignoreCase
Modified:
lucene/dev/trunk/lucene/CHANGES.txt
lucene/dev/trunk/lucene/contrib/CHANGES.txt
lucene/dev/trunk/modules/analysis/CHANGES.txt
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/da/DanishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/es/SpanishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/eu/BasqueAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fi/FinnishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hu/HungarianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hy/ArmenianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/id/IndonesianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/lv/LatvianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/KeywordMarkerFilter.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PatternAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/StemmerOverrideFilter.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/no/NorwegianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ro/RomanianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/snowball/SnowballAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/sv/SwedishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/da/TestDanishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/es/TestSpanishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/eu/TestBasqueAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElision.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/hy/TestArmenianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeywordMarkerFilter.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestStemmerOverrideFilter.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/nl/TestDutchStemmer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/no/TestNorwegianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/ro/TestRomanianAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/sv/TestSwedishAnalyzer.java
lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/tr/TestTurkishAnalyzer.java
lucene/dev/trunk/modules/analysis/kuromoji/src/java/org/apache/lucene/analysis/kuromoji/KuromojiAnalyzer.java
lucene/dev/trunk/modules/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java
lucene/dev/trunk/modules/analysis/stempel/src/java/org/apache/lucene/analysis/pl/PolishAnalyzer.java
lucene/dev/trunk/modules/analysis/stempel/src/test/org/apache/lucene/analysis/pl/TestPolishAnalyzer.java
lucene/dev/trunk/solr/contrib/clustering/src/java/org/apache/solr/handler/clustering/carrot2/SolrStopwordsCarrot2LexicalDataFactory.java
lucene/dev/trunk/solr/core/src/java/org/apache/solr/analysis/CommonGramsFilterFactory.java
lucene/dev/trunk/solr/core/src/java/org/apache/solr/analysis/CommonGramsQueryFilterFactory.java
lucene/dev/trunk/solr/core/src/java/org/apache/solr/analysis/StopFilterFactory.java
lucene/dev/trunk/solr/core/src/test/org/apache/solr/analysis/CommonGramsFilterFactoryTest.java
lucene/dev/trunk/solr/core/src/test/org/apache/solr/analysis/CommonGramsQueryFilterFactoryTest.java
lucene/dev/trunk/solr/core/src/test/org/apache/solr/analysis/TestKeepFilterFactory.java
lucene/dev/trunk/solr/core/src/test/org/apache/solr/analysis/TestStopFilterFactory.java
Modified: lucene/dev/trunk/lucene/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/CHANGES.txt?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/CHANGES.txt (original)
+++ lucene/dev/trunk/lucene/CHANGES.txt Thu Feb 9 19:59:50 2012
@@ -779,6 +779,11 @@ API Changes
to be merged. To mimic the old behaviour, just use IndexReader.directory()
for choosing the provider by Directory. (Uwe Schindler)
+* LUCENE-3765: Deprecated StopFilter ctor that took ignoreCase, because
+ in some cases (if the set is a CharArraySet), the argument is ignored.
+ Deprecated StandardAnalyzer and ClassicAnalyzer ctors that take File,
+ please use the Reader ctor instead. (Robert Muir)
+
New Features
* LUCENE-3593: Added a FieldValueFilter that accepts all documents that either
Modified: lucene/dev/trunk/lucene/contrib/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/CHANGES.txt?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/CHANGES.txt (original)
+++ lucene/dev/trunk/lucene/contrib/CHANGES.txt Thu Feb 9 19:59:50 2012
@@ -218,6 +218,10 @@ Bug Fixes
* LUCENE-3719: FVH: slow performance on very large queries.
(Igor Motov via Koji Sekiguchi)
+ * LUCENE-3765: As of Version.LUCENE_36, DutchAnalyzer's two ctors
+ that take stopwords and stem exclusion tables also initialize
+ the default stem overrides (e.g. kind/kinder, fiets). (Robert Muir)
+
Documentation
* LUCENE-3599: Javadocs for DistanceUtils.haversine() were incorrectly
Modified: lucene/dev/trunk/modules/analysis/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/CHANGES.txt?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/CHANGES.txt (original)
+++ lucene/dev/trunk/modules/analysis/CHANGES.txt Thu Feb 9 19:59:50 2012
@@ -29,6 +29,11 @@ API Changes
since they prevent reuse. Both Analyzers should be configured at instantiation.
(Chris Male)
+ * LUCENE-3765: Stopset ctors that previously took Set<?> or Map<?,String> now take
+ CharArraySet and CharArrayMap respectively. Previously the behavior was confusing,
+ and sometimes different depending on the type of set, and ultimately a CharArraySet
+ or CharArrayMap was always used anyway. (Robert Muir)
+
New Features
* LUCENE-2341: A new analyzer/ filter: Morfologik - a dictionary-driven lemmatizer
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.ar;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -63,7 +62,7 @@ public final class ArabicAnalyzer extend
* Returns an unmodifiable instance of the default stop-words set.
* @return an unmodifiable instance of the default stop-words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -72,7 +71,7 @@ public final class ArabicAnalyzer extend
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -85,7 +84,7 @@ public final class ArabicAnalyzer extend
}
}
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
@@ -102,7 +101,7 @@ public final class ArabicAnalyzer extend
* @param stopwords
* a stopword set
*/
- public ArabicAnalyzer(Version matchVersion, Set<?> stopwords){
+ public ArabicAnalyzer(Version matchVersion, CharArraySet stopwords){
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -118,7 +117,7 @@ public final class ArabicAnalyzer extend
* @param stemExclusionSet
* a set of terms not to be stemmed
*/
- public ArabicAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet){
+ public ArabicAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet){
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -56,7 +56,7 @@ public final class BulgarianAnalyzer ext
*
* @return an unmodifiable instance of the default stop-words set.
*/
- public static Set<?> getDefaultStopSet() {
+ public static CharArraySet getDefaultStopSet() {
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -65,7 +65,7 @@ public final class BulgarianAnalyzer ext
* class accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -78,7 +78,7 @@ public final class BulgarianAnalyzer ext
}
}
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/**
* Builds an analyzer with the default stop words:
@@ -91,7 +91,7 @@ public final class BulgarianAnalyzer ext
/**
* Builds an analyzer with the given stop words.
*/
- public BulgarianAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public BulgarianAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -100,7 +100,7 @@ public final class BulgarianAnalyzer ext
* If a stem exclusion set is provided this analyzer will add a {@link KeywordMarkerFilter}
* before {@link BulgarianStemFilter}.
*/
- public BulgarianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public BulgarianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet)); }
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,8 +19,6 @@ package org.apache.lucene.analysis.br;
import java.io.IOException;
import java.io.Reader;
-import java.util.Collections;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
@@ -56,12 +54,12 @@ public final class BrazilianAnalyzer ext
* Returns an unmodifiable instance of the default stop-words set.
* @return an unmodifiable instance of the default stop-words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -79,7 +77,7 @@ public final class BrazilianAnalyzer ext
/**
* Contains words that should be indexed but not stemmed.
*/
- private Set<?> excltable = Collections.emptySet();
+ private CharArraySet excltable = CharArraySet.EMPTY_SET;
/**
* Builds an analyzer with the default stop words ({@link #getDefaultStopSet()}).
@@ -96,7 +94,7 @@ public final class BrazilianAnalyzer ext
* @param stopwords
* a stopword set
*/
- public BrazilianAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public BrazilianAnalyzer(Version matchVersion, CharArraySet stopwords) {
super(matchVersion, stopwords);
}
@@ -108,8 +106,8 @@ public final class BrazilianAnalyzer ext
* @param stopwords
* a stopword set
*/
- public BrazilianAnalyzer(Version matchVersion, Set<?> stopwords,
- Set<?> stemExclusionSet) {
+ public BrazilianAnalyzer(Version matchVersion, CharArraySet stopwords,
+ CharArraySet stemExclusionSet) {
this(matchVersion, stopwords);
excltable = CharArraySet.unmodifiableSet(CharArraySet
.copy(matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -20,7 +20,6 @@ package org.apache.lucene.analysis.ca;
import java.io.IOException;
import java.io.Reader;
import java.util.Arrays;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -49,7 +48,7 @@ import org.tartarus.snowball.ext.Catalan
* </ul>
*/
public final class CatalanAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Catalan stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
@@ -64,7 +63,7 @@ public final class CatalanAnalyzer exten
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -73,7 +72,7 @@ public final class CatalanAnalyzer exten
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -100,7 +99,7 @@ public final class CatalanAnalyzer exten
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public CatalanAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public CatalanAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -113,7 +112,7 @@ public final class CatalanAnalyzer exten
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public CatalanAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public CatalanAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.cjk;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
@@ -27,6 +26,7 @@ import org.apache.lucene.analysis.Tokeni
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.util.Version;
@@ -49,12 +49,12 @@ public final class CJKAnalyzer extends S
* Returns an unmodifiable instance of the default stop-words set.
* @return an unmodifiable instance of the default stop-words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -82,7 +82,7 @@ public final class CJKAnalyzer extends S
* @param stopwords
* a stopword set
*/
- public CJKAnalyzer(Version matchVersion, Set<?> stopwords){
+ public CJKAnalyzer(Version matchVersion, CharArraySet stopwords){
super(matchVersion, stopwords);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java Thu Feb 9 19:59:50 2012
@@ -10,7 +10,6 @@
package org.apache.lucene.analysis.commongrams;
import java.io.IOException;
-import java.util.Set;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
@@ -69,35 +68,9 @@ public final class CommonGramsFilter ext
* @param input TokenStream input in filter chain
* @param commonWords The set of common words.
*/
- public CommonGramsFilter(Version matchVersion, TokenStream input, Set<?> commonWords) {
- this(matchVersion, input, commonWords, false);
- }
-
- /**
- * Construct a token stream filtering the given input using a Set of common
- * words to create bigrams, case-sensitive if ignoreCase is false (unless Set
- * is CharArraySet). If <code>commonWords</code> is an instance of
- * {@link CharArraySet} (true if <code>makeCommonSet()</code> was used to
- * construct the set) it will be directly used and <code>ignoreCase</code>
- * will be ignored since <code>CharArraySet</code> directly controls case
- * sensitivity.
- * <p/>
- * If <code>commonWords</code> is not an instance of {@link CharArraySet}, a
- * new CharArraySet will be constructed and <code>ignoreCase</code> will be
- * used to specify the case sensitivity of that set.
- *
- * @param input TokenStream input in filter chain.
- * @param commonWords The set of common words.
- * @param ignoreCase -Ignore case when constructing bigrams for common words.
- */
- public CommonGramsFilter(Version matchVersion, TokenStream input, Set<?> commonWords, boolean ignoreCase) {
+ public CommonGramsFilter(Version matchVersion, TokenStream input, CharArraySet commonWords) {
super(input);
- if (commonWords instanceof CharArraySet) {
- this.commonWords = (CharArraySet) commonWords;
- } else {
- this.commonWords = new CharArraySet(matchVersion, commonWords.size(), ignoreCase);
- this.commonWords.addAll(commonWords);
- }
+ this.commonWords = commonWords;
}
/**
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java Thu Feb 9 19:59:50 2012
@@ -18,10 +18,7 @@ package org.apache.lucene.analysis.compo
*/
import java.io.IOException;
-import java.util.Arrays;
-import java.util.Collection;
import java.util.LinkedList;
-import java.util.Locale;
import java.util.Set;
import org.apache.lucene.analysis.TokenFilter;
@@ -43,13 +40,6 @@ import org.apache.lucene.util.Version;
* supplementary characters in strings and char arrays provided as compound word
* dictionaries.
* </ul>
- * <p>If you pass in a {@link org.apache.lucene.analysis.util.CharArraySet} as dictionary,
- * it should be case-insensitive unless it contains only lowercased entries and you
- * have {@link org.apache.lucene.analysis.core.LowerCaseFilter} before this filter in your analysis chain.
- * For optional performance (as this filter does lots of lookups to the dictionary,
- * you should use the latter analysis chain/CharArraySet). Be aware: If you supply arbitrary
- * {@link Set Sets} to the ctors, they will be automatically
- * transformed to case-insensitive!
*/
public abstract class CompoundWordTokenFilterBase extends TokenFilter {
/**
@@ -80,15 +70,15 @@ public abstract class CompoundWordTokenF
private AttributeSource.State current;
- protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, Set<?> dictionary, boolean onlyLongestMatch) {
+ protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, CharArraySet dictionary, boolean onlyLongestMatch) {
this(matchVersion, input,dictionary,DEFAULT_MIN_WORD_SIZE,DEFAULT_MIN_SUBWORD_SIZE,DEFAULT_MAX_SUBWORD_SIZE, onlyLongestMatch);
}
- protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, Set<?> dictionary) {
+ protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, CharArraySet dictionary) {
this(matchVersion, input,dictionary,DEFAULT_MIN_WORD_SIZE,DEFAULT_MIN_SUBWORD_SIZE,DEFAULT_MAX_SUBWORD_SIZE, false);
}
- protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, Set<?> dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
+ protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, CharArraySet dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
super(input);
this.tokens=new LinkedList<CompoundToken>();
@@ -96,12 +86,7 @@ public abstract class CompoundWordTokenF
this.minSubwordSize=minSubwordSize;
this.maxSubwordSize=maxSubwordSize;
this.onlyLongestMatch=onlyLongestMatch;
-
- if (dictionary==null || dictionary instanceof CharArraySet) {
- this.dictionary = (CharArraySet) dictionary;
- } else {
- this.dictionary = new CharArraySet(matchVersion, dictionary, true);
- }
+ this.dictionary = dictionary;
}
@Override
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java Thu Feb 9 19:59:50 2012
@@ -22,6 +22,7 @@ import java.util.Set;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
/**
@@ -38,13 +39,6 @@ import org.apache.lucene.util.Version;
* supplementary characters in strings and char arrays provided as compound word
* dictionaries.
* </ul>
- * <p>If you pass in a {@link org.apache.lucene.analysis.util.CharArraySet} as dictionary,
- * it should be case-insensitive unless it contains only lowercased entries and you
- * have {@link org.apache.lucene.analysis.core.LowerCaseFilter} before this filter in your analysis chain.
- * For optional performance (as this filter does lots of lookups to the dictionary,
- * you should use the latter analysis chain/CharArraySet). Be aware: If you supply arbitrary
- * {@link Set Sets} to the ctors, they will be automatically
- * transformed to case-insensitive!
*/
public class DictionaryCompoundWordTokenFilter extends CompoundWordTokenFilterBase {
@@ -61,7 +55,7 @@ public class DictionaryCompoundWordToken
* @param dictionary
* the word dictionary to match against.
*/
- public DictionaryCompoundWordTokenFilter(Version matchVersion, TokenStream input, Set<?> dictionary) {
+ public DictionaryCompoundWordTokenFilter(Version matchVersion, TokenStream input, CharArraySet dictionary) {
super(matchVersion, input, dictionary);
}
@@ -86,7 +80,7 @@ public class DictionaryCompoundWordToken
* @param onlyLongestMatch
* Add only the longest matching subword to the stream
*/
- public DictionaryCompoundWordTokenFilter(Version matchVersion, TokenStream input, Set<?> dictionary,
+ public DictionaryCompoundWordTokenFilter(Version matchVersion, TokenStream input, CharArraySet dictionary,
int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
super(matchVersion, input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java Thu Feb 9 19:59:50 2012
@@ -18,12 +18,12 @@ package org.apache.lucene.analysis.compo
*/
import java.io.File;
-import java.util.Set;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.compound.hyphenation.Hyphenation;
import org.apache.lucene.analysis.compound.hyphenation.HyphenationTree;
+import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
import org.xml.sax.InputSource;
@@ -41,13 +41,6 @@ import org.xml.sax.InputSource;
* supplementary characters in strings and char arrays provided as compound word
* dictionaries.
* </ul>
- * <p>If you pass in a {@link org.apache.lucene.analysis.util.CharArraySet} as dictionary,
- * it should be case-insensitive unless it contains only lowercased entries and you
- * have {@link org.apache.lucene.analysis.core.LowerCaseFilter} before this filter in your analysis chain.
- * For optional performance (as this filter does lots of lookups to the dictionary,
- * you should use the latter analysis chain/CharArraySet). Be aware: If you supply arbitrary
- * {@link Set Sets} to the ctors, they will be automatically
- * transformed to case-insensitive!
*/
public class HyphenationCompoundWordTokenFilter extends
CompoundWordTokenFilterBase {
@@ -69,7 +62,7 @@ public class HyphenationCompoundWordToke
* the word dictionary to match against.
*/
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input,
- HyphenationTree hyphenator, Set<?> dictionary) {
+ HyphenationTree hyphenator, CharArraySet dictionary) {
this(matchVersion, input, hyphenator, dictionary, DEFAULT_MIN_WORD_SIZE,
DEFAULT_MIN_SUBWORD_SIZE, DEFAULT_MAX_SUBWORD_SIZE, false);
}
@@ -98,7 +91,7 @@ public class HyphenationCompoundWordToke
* Add only the longest matching subword to the stream
*/
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input,
- HyphenationTree hyphenator, Set<?> dictionary, int minWordSize,
+ HyphenationTree hyphenator, CharArraySet dictionary, int minWordSize,
int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
super(matchVersion, input, dictionary, minWordSize, minSubwordSize, maxSubwordSize,
onlyLongestMatch);
@@ -109,14 +102,14 @@ public class HyphenationCompoundWordToke
/**
* Create a HyphenationCompoundWordTokenFilter with no dictionary.
* <p>
- * Calls {@link #HyphenationCompoundWordTokenFilter(Version, TokenStream, HyphenationTree, Set, int, int, int, boolean)
+ * Calls {@link #HyphenationCompoundWordTokenFilter(Version, TokenStream, HyphenationTree, CharArraySet, int, int, int, boolean)
* HyphenationCompoundWordTokenFilter(matchVersion, input, hyphenator,
* null, minWordSize, minSubwordSize, maxSubwordSize }
*/
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input,
HyphenationTree hyphenator, int minWordSize, int minSubwordSize,
int maxSubwordSize) {
- this(matchVersion, input, hyphenator, (Set<?>) null, minWordSize, minSubwordSize,
+ this(matchVersion, input, hyphenator, null, minWordSize, minSubwordSize,
maxSubwordSize, false);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -21,7 +21,6 @@ import java.io.File;
import java.io.IOException;
import java.io.Reader;
import java.util.Arrays;
-import java.util.Set;
import java.util.List;
import org.apache.lucene.analysis.Tokenizer;
@@ -46,7 +45,7 @@ public final class StopAnalyzer extends
/** An unmodifiable set containing some common English words that are not usually useful
for searching.*/
- public static final Set<?> ENGLISH_STOP_WORDS_SET;
+ public static final CharArraySet ENGLISH_STOP_WORDS_SET;
static {
final List<String> stopWords = Arrays.asList(
@@ -72,7 +71,7 @@ public final class StopAnalyzer extends
/** Builds an analyzer with the stop words from the given set.
* @param matchVersion See <a href="#version">above</a>
* @param stopWords Set of stop words */
- public StopAnalyzer(Version matchVersion, Set<?> stopWords) {
+ public StopAnalyzer(Version matchVersion, CharArraySet stopWords) {
super(matchVersion, stopWords);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java Thu Feb 9 19:59:50 2012
@@ -20,7 +20,6 @@ package org.apache.lucene.analysis.core;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
-import java.util.Set;
import org.apache.lucene.analysis.util.FilteringTokenFilter;
import org.apache.lucene.analysis.TokenStream;
@@ -44,34 +43,6 @@ public final class StopFilter extends Fi
private final CharArraySet stopWords;
private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
-
- /**
- * Construct a token stream filtering the given input. If
- * <code>stopWords</code> is an instance of {@link CharArraySet} (true if
- * <code>makeStopSet()</code> was used to construct the set) it will be
- * directly used and <code>ignoreCase</code> will be ignored since
- * <code>CharArraySet</code> directly controls case sensitivity.
- * <p/>
- * If <code>stopWords</code> is not an instance of {@link CharArraySet}, a new
- * CharArraySet will be constructed and <code>ignoreCase</code> will be used
- * to specify the case sensitivity of that set.
- *
- * @param matchVersion
- * Lucene version to enable correct Unicode 4.0 behavior in the stop
- * set if Version > 3.0. See <a href="#version">above</a> for details.
- * @param input
- * Input TokenStream
- * @param stopWords
- * A Set of Strings or char[] or any other toString()-able set
- * representing the stopwords
- * @param ignoreCase
- * if true, all words are lower cased first
- */
- public StopFilter(Version matchVersion, TokenStream input, Set<?> stopWords, boolean ignoreCase)
- {
- super(true, input);
- this.stopWords = stopWords instanceof CharArraySet ? (CharArraySet) stopWords : new CharArraySet(matchVersion, stopWords, ignoreCase);
- }
/**
* Constructs a filter which removes words from the input TokenStream that are
@@ -83,12 +54,12 @@ public final class StopFilter extends Fi
* @param in
* Input stream
* @param stopWords
- * A Set of Strings or char[] or any other toString()-able set
- * representing the stopwords
+ * A {@link CharArraySet} representing the stopwords.
* @see #makeStopSet(Version, java.lang.String...)
*/
- public StopFilter(Version matchVersion, TokenStream in, Set<?> stopWords) {
- this(matchVersion, in, stopWords, false);
+ public StopFilter(Version matchVersion, TokenStream in, CharArraySet stopWords) {
+ super(true, in);
+ this.stopWords = stopWords;
}
/**
@@ -101,7 +72,7 @@ public final class StopFilter extends Fi
* @param stopWords An array of stopwords
* @see #makeStopSet(Version, java.lang.String[], boolean) passing false to ignoreCase
*/
- public static Set<Object> makeStopSet(Version matchVersion, String... stopWords) {
+ public static CharArraySet makeStopSet(Version matchVersion, String... stopWords) {
return makeStopSet(matchVersion, stopWords, false);
}
@@ -116,7 +87,7 @@ public final class StopFilter extends Fi
* @return A Set ({@link CharArraySet}) containing the words
* @see #makeStopSet(Version, java.lang.String[], boolean) passing false to ignoreCase
*/
- public static Set<Object> makeStopSet(Version matchVersion, List<?> stopWords) {
+ public static CharArraySet makeStopSet(Version matchVersion, List<?> stopWords) {
return makeStopSet(matchVersion, stopWords, false);
}
@@ -128,7 +99,7 @@ public final class StopFilter extends Fi
* @param ignoreCase If true, all words are lower cased first.
* @return a Set containing the words
*/
- public static Set<Object> makeStopSet(Version matchVersion, String[] stopWords, boolean ignoreCase) {
+ public static CharArraySet makeStopSet(Version matchVersion, String[] stopWords, boolean ignoreCase) {
CharArraySet stopSet = new CharArraySet(matchVersion, stopWords.length, ignoreCase);
stopSet.addAll(Arrays.asList(stopWords));
return stopSet;
@@ -141,7 +112,7 @@ public final class StopFilter extends Fi
* @param ignoreCase if true, all words are lower cased first
* @return A Set ({@link CharArraySet}) containing the words
*/
- public static Set<Object> makeStopSet(Version matchVersion, List<?> stopWords, boolean ignoreCase){
+ public static CharArraySet makeStopSet(Version matchVersion, List<?> stopWords, boolean ignoreCase){
CharArraySet stopSet = new CharArraySet(matchVersion, stopWords.size(), ignoreCase);
stopSet.addAll(stopWords);
return stopSet;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -32,7 +32,6 @@ import org.apache.lucene.util.IOUtils;
import org.apache.lucene.util.Version;
import java.io.*;
-import java.util.Set;
/**
* {@link Analyzer} for Czech language.
@@ -62,12 +61,12 @@ public final class CzechAnalyzer extends
*
* @return a set of default Czech-stopwords
*/
- public static final Set<?> getDefaultStopSet(){
+ public static final CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_SET;
}
private static class DefaultSetHolder {
- private static final Set<?> DEFAULT_SET;
+ private static final CharArraySet DEFAULT_SET;
static {
try {
@@ -82,7 +81,7 @@ public final class CzechAnalyzer extends
}
- private final Set<?> stemExclusionTable;
+ private final CharArraySet stemExclusionTable;
/**
* Builds an analyzer with the default stop words ({@link #getDefaultStopSet()}).
@@ -101,7 +100,7 @@ public final class CzechAnalyzer extends
* {@link <a href="#version">above</a>}
* @param stopwords a stopword set
*/
- public CzechAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public CzechAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -114,7 +113,7 @@ public final class CzechAnalyzer extends
* @param stopwords a stopword set
* @param stemExclusionTable a stemming exclusion set
*/
- public CzechAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionTable) {
+ public CzechAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionTable) {
super(matchVersion, stopwords);
this.stemExclusionTable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionTable));
}
@@ -129,7 +128,7 @@ public final class CzechAnalyzer extends
* {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
* , and {@link CzechStemFilter} (only if version is >= LUCENE_31). If
* a version is >= LUCENE_31 and a stem exclusion set is provided via
- * {@link #CzechAnalyzer(Version, Set, Set)} a
+ * {@link #CzechAnalyzer(Version, CharArraySet, CharArraySet)} a
* {@link KeywordMarkerFilter} is added before
* {@link CzechStemFilter}.
*/
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/da/DanishAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/da/DanishAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/da/DanishAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/da/DanishAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.da;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -41,7 +40,7 @@ import org.tartarus.snowball.ext.DanishS
* {@link Analyzer} for Danish.
*/
public final class DanishAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Danish stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "danish_stop.txt";
@@ -50,7 +49,7 @@ public final class DanishAnalyzer extend
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -59,7 +58,7 @@ public final class DanishAnalyzer extend
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -86,7 +85,7 @@ public final class DanishAnalyzer extend
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public DanishAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public DanishAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -99,7 +98,7 @@ public final class DanishAnalyzer extend
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public DanishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public DanishAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -21,7 +21,6 @@ package org.apache.lucene.analysis.de;
import java.io.IOException;
import java.io.Reader;
import java.util.Arrays;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -90,16 +89,16 @@ public final class GermanAnalyzer extend
* Returns a set of default German-stopwords
* @return a set of default German-stopwords
*/
- public static final Set<?> getDefaultStopSet(){
+ public static final CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_SET;
}
private static class DefaultSetHolder {
/** @deprecated in 3.1, remove in Lucene 5.0 (index bw compat) */
@Deprecated
- private static final Set<?> DEFAULT_SET_30 = CharArraySet.unmodifiableSet(new CharArraySet(
+ private static final CharArraySet DEFAULT_SET_30 = CharArraySet.unmodifiableSet(new CharArraySet(
Version.LUCENE_CURRENT, Arrays.asList(GERMAN_STOP_WORDS), false));
- private static final Set<?> DEFAULT_SET;
+ private static final CharArraySet DEFAULT_SET;
static {
try {
DEFAULT_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
@@ -119,7 +118,7 @@ public final class GermanAnalyzer extend
/**
* Contains words that should be indexed but not stemmed.
*/
- private final Set<?> exclusionSet;
+ private final CharArraySet exclusionSet;
/**
* Builds an analyzer with the default stop words:
@@ -139,7 +138,7 @@ public final class GermanAnalyzer extend
* @param stopwords
* a stopword set
*/
- public GermanAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public GermanAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -153,7 +152,7 @@ public final class GermanAnalyzer extend
* @param stemExclusionSet
* a stemming exclusion set
*/
- public GermanAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public GermanAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
exclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet));
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -18,7 +18,6 @@ package org.apache.lucene.analysis.el;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
@@ -27,6 +26,7 @@ import org.apache.lucene.analysis.core.S
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.util.Version;
@@ -58,12 +58,12 @@ public final class GreekAnalyzer extends
* Returns a set of default Greek-stopwords
* @return a set of default Greek-stopwords
*/
- public static final Set<?> getDefaultStopSet(){
+ public static final CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_SET;
}
private static class DefaultSetHolder {
- private static final Set<?> DEFAULT_SET;
+ private static final CharArraySet DEFAULT_SET;
static {
try {
@@ -95,7 +95,7 @@ public final class GreekAnalyzer extends
* See <a href="#version">above</a>
* @param stopwords a stopword set
*/
- public GreekAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public GreekAnalyzer(Version matchVersion, CharArraySet stopwords) {
super(matchVersion, stopwords);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -18,7 +18,6 @@ package org.apache.lucene.analysis.en;
*/
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
@@ -37,13 +36,13 @@ import org.apache.lucene.util.Version;
* {@link Analyzer} for English.
*/
public final class EnglishAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/**
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -52,7 +51,7 @@ public final class EnglishAnalyzer exten
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET = StandardAnalyzer.STOP_WORDS_SET;
+ static final CharArraySet DEFAULT_STOP_SET = StandardAnalyzer.STOP_WORDS_SET;
}
/**
@@ -68,7 +67,7 @@ public final class EnglishAnalyzer exten
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public EnglishAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public EnglishAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -81,7 +80,7 @@ public final class EnglishAnalyzer exten
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public EnglishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public EnglishAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/es/SpanishAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/es/SpanishAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/es/SpanishAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/es/SpanishAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.es;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -48,7 +47,7 @@ import org.tartarus.snowball.ext.Spanish
* </ul>
*/
public final class SpanishAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Spanish stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "spanish_stop.txt";
@@ -57,7 +56,7 @@ public final class SpanishAnalyzer exten
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -66,7 +65,7 @@ public final class SpanishAnalyzer exten
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -93,7 +92,7 @@ public final class SpanishAnalyzer exten
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public SpanishAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public SpanishAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -106,7 +105,7 @@ public final class SpanishAnalyzer exten
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public SpanishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public SpanishAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/eu/BasqueAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/eu/BasqueAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/eu/BasqueAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/eu/BasqueAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.eu;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -39,7 +38,7 @@ import org.tartarus.snowball.ext.BasqueS
* {@link Analyzer} for Basque.
*/
public final class BasqueAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Basque stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
@@ -48,7 +47,7 @@ public final class BasqueAnalyzer extend
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -57,7 +56,7 @@ public final class BasqueAnalyzer extend
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -84,7 +83,7 @@ public final class BasqueAnalyzer extend
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public BasqueAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public BasqueAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -97,7 +96,7 @@ public final class BasqueAnalyzer extend
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public BasqueAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public BasqueAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.fa;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharReader;
@@ -30,6 +29,7 @@ import org.apache.lucene.analysis.ar.Ara
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.util.Version;
@@ -63,7 +63,7 @@ public final class PersianAnalyzer exten
* Returns an unmodifiable instance of the default stop-words set.
* @return an unmodifiable instance of the default stop-words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -72,7 +72,7 @@ public final class PersianAnalyzer exten
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -101,7 +101,7 @@ public final class PersianAnalyzer exten
* @param stopwords
* a stopword set
*/
- public PersianAnalyzer(Version matchVersion, Set<?> stopwords){
+ public PersianAnalyzer(Version matchVersion, CharArraySet stopwords){
super(matchVersion, stopwords);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fi/FinnishAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fi/FinnishAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fi/FinnishAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fi/FinnishAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.fi;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -41,7 +40,7 @@ import org.tartarus.snowball.ext.Finnish
* {@link Analyzer} for Finnish.
*/
public final class FinnishAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Italian stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "finnish_stop.txt";
@@ -50,7 +49,7 @@ public final class FinnishAnalyzer exten
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -59,7 +58,7 @@ public final class FinnishAnalyzer exten
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -86,7 +85,7 @@ public final class FinnishAnalyzer exten
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public FinnishAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public FinnishAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -99,7 +98,7 @@ public final class FinnishAnalyzer exten
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public FinnishAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public FinnishAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java Thu Feb 9 19:59:50 2012
@@ -19,11 +19,9 @@ package org.apache.lucene.analysis.fr;
import java.io.IOException;
import java.util.Arrays;
-import java.util.Set;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
@@ -56,7 +54,7 @@ public final class ElisionFilter extends
* @param input the source {@link TokenStream}
* @param articles a set of stopword articles
*/
- public ElisionFilter(Version matchVersion, TokenStream input, Set<?> articles) {
+ public ElisionFilter(Version matchVersion, TokenStream input, CharArraySet articles) {
super(input);
this.articles = CharArraySet.unmodifiableSet(
new CharArraySet(matchVersion, articles, true));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -36,7 +36,6 @@ import org.apache.lucene.util.Version;
import java.io.IOException;
import java.io.Reader;
import java.util.Arrays;
-import java.util.Set;
/**
* {@link Analyzer} for French language.
@@ -101,23 +100,23 @@ public final class FrenchAnalyzer extend
/**
* Contains words that should be indexed but not stemmed.
*/
- private final Set<?> excltable;
+ private final CharArraySet excltable;
/**
* Returns an unmodifiable instance of the default stop-words set.
* @return an unmodifiable instance of the default stop-words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
private static class DefaultSetHolder {
/** @deprecated (3.1) remove this in Lucene 5.0, index bw compat */
@Deprecated
- static final Set<?> DEFAULT_STOP_SET_30 = CharArraySet
+ static final CharArraySet DEFAULT_STOP_SET_30 = CharArraySet
.unmodifiableSet(new CharArraySet(Version.LUCENE_CURRENT, Arrays.asList(FRENCH_STOP_WORDS),
false));
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class,
@@ -147,7 +146,7 @@ public final class FrenchAnalyzer extend
* @param stopwords
* a stopword set
*/
- public FrenchAnalyzer(Version matchVersion, Set<?> stopwords){
+ public FrenchAnalyzer(Version matchVersion, CharArraySet stopwords){
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -161,8 +160,8 @@ public final class FrenchAnalyzer extend
* @param stemExclutionSet
* a stemming exclusion set
*/
- public FrenchAnalyzer(Version matchVersion, Set<?> stopwords,
- Set<?> stemExclutionSet) {
+ public FrenchAnalyzer(Version matchVersion, CharArraySet stopwords,
+ CharArraySet stemExclutionSet) {
super(matchVersion, stopwords);
this.excltable = CharArraySet.unmodifiableSet(CharArraySet
.copy(matchVersion, stemExclutionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.gl;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -39,7 +38,7 @@ import org.apache.lucene.util.Version;
* {@link Analyzer} for Galician.
*/
public final class GalicianAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Galician stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
@@ -48,7 +47,7 @@ public final class GalicianAnalyzer exte
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -57,7 +56,7 @@ public final class GalicianAnalyzer exte
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -84,7 +83,7 @@ public final class GalicianAnalyzer exte
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public GalicianAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public GalicianAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -97,7 +96,7 @@ public final class GalicianAnalyzer exte
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public GalicianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public GalicianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.hi;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
@@ -44,7 +43,7 @@ import org.apache.lucene.util.Version;
* </ul>
*/
public final class HindiAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/**
* File containing default Hindi stopwords.
@@ -59,7 +58,7 @@ public final class HindiAnalyzer extends
* Returns an unmodifiable instance of the default stop-words set.
* @return an unmodifiable instance of the default stop-words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -68,7 +67,7 @@ public final class HindiAnalyzer extends
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -88,7 +87,7 @@ public final class HindiAnalyzer extends
* @param stopwords a stopword set
* @param stemExclusionSet a stemming exclusion set
*/
- public HindiAnalyzer(Version version, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public HindiAnalyzer(Version version, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(version, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(
CharArraySet.copy(matchVersion, stemExclusionSet));
@@ -100,7 +99,7 @@ public final class HindiAnalyzer extends
* @param version lucene compatibility version
* @param stopwords a stopword set
*/
- public HindiAnalyzer(Version version, Set<?> stopwords) {
+ public HindiAnalyzer(Version version, CharArraySet stopwords) {
this(version, stopwords, CharArraySet.EMPTY_SET);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hu/HungarianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hu/HungarianAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hu/HungarianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hu/HungarianAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.hu;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -41,7 +40,7 @@ import org.tartarus.snowball.ext.Hungari
* {@link Analyzer} for Hungarian.
*/
public final class HungarianAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Hungarian stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "hungarian_stop.txt";
@@ -50,7 +49,7 @@ public final class HungarianAnalyzer ext
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -59,7 +58,7 @@ public final class HungarianAnalyzer ext
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -86,7 +85,7 @@ public final class HungarianAnalyzer ext
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public HungarianAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public HungarianAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -99,7 +98,7 @@ public final class HungarianAnalyzer ext
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public HungarianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public HungarianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hy/ArmenianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hy/ArmenianAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hy/ArmenianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hy/ArmenianAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.hy;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -39,7 +38,7 @@ import org.tartarus.snowball.ext.Armenia
* {@link Analyzer} for Armenian.
*/
public final class ArmenianAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Armenian stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
@@ -48,7 +47,7 @@ public final class ArmenianAnalyzer exte
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -57,7 +56,7 @@ public final class ArmenianAnalyzer exte
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -84,7 +83,7 @@ public final class ArmenianAnalyzer exte
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public ArmenianAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public ArmenianAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -97,7 +96,7 @@ public final class ArmenianAnalyzer exte
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public ArmenianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public ArmenianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/id/IndonesianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/id/IndonesianAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/id/IndonesianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/id/IndonesianAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.id;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopFilter;
@@ -43,7 +42,7 @@ public final class IndonesianAnalyzer ex
* Returns an unmodifiable instance of the default stop-words set.
* @return an unmodifiable instance of the default stop-words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -52,7 +51,7 @@ public final class IndonesianAnalyzer ex
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -65,7 +64,7 @@ public final class IndonesianAnalyzer ex
}
}
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
@@ -82,7 +81,7 @@ public final class IndonesianAnalyzer ex
* @param stopwords
* a stopword set
*/
- public IndonesianAnalyzer(Version matchVersion, Set<?> stopwords){
+ public IndonesianAnalyzer(Version matchVersion, CharArraySet stopwords){
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -98,7 +97,7 @@ public final class IndonesianAnalyzer ex
* @param stemExclusionSet
* a set of terms not to be stemmed
*/
- public IndonesianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet){
+ public IndonesianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet){
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java?rev=1242497&r1=1242496&r2=1242497&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java Thu Feb 9 19:59:50 2012
@@ -20,7 +20,6 @@ package org.apache.lucene.analysis.it;
import java.io.IOException;
import java.io.Reader;
import java.util.Arrays;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -52,7 +51,7 @@ import org.tartarus.snowball.ext.Italian
* </ul>
*/
public final class ItalianAnalyzer extends StopwordAnalyzerBase {
- private final Set<?> stemExclusionSet;
+ private final CharArraySet stemExclusionSet;
/** File containing default Italian stopwords. */
public final static String DEFAULT_STOPWORD_FILE = "italian_stop.txt";
@@ -68,7 +67,7 @@ public final class ItalianAnalyzer exten
* Returns an unmodifiable instance of the default stop words set.
* @return default stop words set.
*/
- public static Set<?> getDefaultStopSet(){
+ public static CharArraySet getDefaultStopSet(){
return DefaultSetHolder.DEFAULT_STOP_SET;
}
@@ -77,7 +76,7 @@ public final class ItalianAnalyzer exten
* accesses the static final set the first time.;
*/
private static class DefaultSetHolder {
- static final Set<?> DEFAULT_STOP_SET;
+ static final CharArraySet DEFAULT_STOP_SET;
static {
try {
@@ -104,7 +103,7 @@ public final class ItalianAnalyzer exten
* @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
- public ItalianAnalyzer(Version matchVersion, Set<?> stopwords) {
+ public ItalianAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -117,7 +116,7 @@ public final class ItalianAnalyzer exten
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
- public ItalianAnalyzer(Version matchVersion, Set<?> stopwords, Set<?> stemExclusionSet) {
+ public ItalianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
matchVersion, stemExclusionSet));