Index: lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestElisionFilterFactory.java =================================================================== --- lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestElisionFilterFactory.java (working copy) +++ lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestElisionFilterFactory.java (working copy) @@ -1,4 +1,4 @@ -package org.apache.lucene.analysis.fr; +package org.apache.lucene.analysis.util; /* * Licensed to the Apache Software Foundation (ASF) under one or more Index: lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestElision.java =================================================================== --- lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestElision.java (working copy) +++ lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestElision.java (working copy) @@ -1,4 +1,4 @@ -package org.apache.lucene.analysis.fr; +package org.apache.lucene.analysis.util; /* * Licensed to the Apache Software Foundation (ASF) under one or more @@ -28,6 +28,7 @@ import org.apache.lucene.analysis.TokenFilter; import org.apache.lucene.analysis.Tokenizer; import org.apache.lucene.analysis.core.KeywordTokenizer; +import org.apache.lucene.analysis.fr.FrenchAnalyzer; import org.apache.lucene.analysis.standard.StandardTokenizer; import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; import org.apache.lucene.analysis.util.CharArraySet; @@ -41,7 +42,7 @@ String test = "Plop, juste pour voir l'embrouille avec O'brian. M'enfin."; Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(test)); CharArraySet articles = new CharArraySet(TEST_VERSION_CURRENT, asSet("l", "M"), false); - TokenFilter filter = new ElisionFilter(TEST_VERSION_CURRENT, tokenizer, articles); + TokenFilter filter = new ElisionFilter(tokenizer, articles); List tas = filter(filter); assertEquals("embrouille", tas.get(4)); assertEquals("O'brian", tas.get(6)); @@ -62,7 +63,7 @@ @Override protected TokenStreamComponents createComponents(String fieldName, Reader reader) { Tokenizer tokenizer = new KeywordTokenizer(reader); - return new TokenStreamComponents(tokenizer, new ElisionFilter(TEST_VERSION_CURRENT, tokenizer)); + return new TokenStreamComponents(tokenizer, new ElisionFilter(tokenizer, FrenchAnalyzer.DEFAULT_ARTICLES)); } }; checkOneTermReuse(a, "", ""); Index: lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElision.java =================================================================== --- lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElision.java (revision 1366186) +++ lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElision.java (working copy) @@ -1,71 +0,0 @@ -package org.apache.lucene.analysis.fr; - -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import java.io.IOException; -import java.io.Reader; -import java.io.StringReader; -import java.util.ArrayList; -import java.util.List; - -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.BaseTokenStreamTestCase; -import org.apache.lucene.analysis.TokenFilter; -import org.apache.lucene.analysis.Tokenizer; -import org.apache.lucene.analysis.core.KeywordTokenizer; -import org.apache.lucene.analysis.standard.StandardTokenizer; -import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; -import org.apache.lucene.analysis.util.CharArraySet; - -/** - * - */ -public class TestElision extends BaseTokenStreamTestCase { - - public void testElision() throws Exception { - String test = "Plop, juste pour voir l'embrouille avec O'brian. M'enfin."; - Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(test)); - CharArraySet articles = new CharArraySet(TEST_VERSION_CURRENT, asSet("l", "M"), false); - TokenFilter filter = new ElisionFilter(TEST_VERSION_CURRENT, tokenizer, articles); - List tas = filter(filter); - assertEquals("embrouille", tas.get(4)); - assertEquals("O'brian", tas.get(6)); - assertEquals("enfin", tas.get(7)); - } - - private List filter(TokenFilter filter) throws IOException { - List tas = new ArrayList(); - CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class); - while (filter.incrementToken()) { - tas.add(termAtt.toString()); - } - return tas; - } - - public void testEmptyTerm() throws IOException { - Analyzer a = new Analyzer() { - @Override - protected TokenStreamComponents createComponents(String fieldName, Reader reader) { - Tokenizer tokenizer = new KeywordTokenizer(reader); - return new TokenStreamComponents(tokenizer, new ElisionFilter(TEST_VERSION_CURRENT, tokenizer)); - } - }; - checkOneTermReuse(a, "", ""); - } - -} Index: lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/frenchArticles.txt =================================================================== --- lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/frenchArticles.txt (revision 1366186) +++ lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/frenchArticles.txt (working copy) @@ -1,24 +0,0 @@ -# Licensed to the Apache Software Foundation (ASF) under one or more -# contributor license agreements. See the NOTICE file distributed with -# this work for additional information regarding copyright ownership. -# The ASF licenses this file to You under the Apache License, Version 2.0 -# (the "License"); you may not use this file except in compliance with -# the License. You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. -# -# A set of articles for testing the French Elision filter. -# Requiring a text file is a bit weird here... -l -m -t -qu -n -s -j Index: lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElisionFilterFactory.java =================================================================== --- lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElisionFilterFactory.java (revision 1366186) +++ lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElisionFilterFactory.java (working copy) @@ -1,88 +0,0 @@ -package org.apache.lucene.analysis.fr; - -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import java.io.Reader; -import java.io.StringReader; -import java.util.Collections; -import java.util.HashMap; -import java.util.Map; - -import org.apache.lucene.analysis.BaseTokenStreamTestCase; -import org.apache.lucene.analysis.MockTokenizer; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.Tokenizer; -import org.apache.lucene.analysis.util.ResourceAsStreamResourceLoader; -import org.apache.lucene.analysis.util.ResourceLoader; - -/** - * Simple tests to ensure the French elision filter factory is working. - */ -public class TestElisionFilterFactory extends BaseTokenStreamTestCase { - /** - * Ensure the filter actually normalizes text. - */ - public void testElision() throws Exception { - Reader reader = new StringReader("l'avion"); - Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false); - ElisionFilterFactory factory = new ElisionFilterFactory(); - factory.setLuceneMatchVersion(TEST_VERSION_CURRENT); - ResourceLoader loader = new ResourceAsStreamResourceLoader(getClass()); - Map args = new HashMap(); - args.put("articles", "frenchArticles.txt"); - factory.init(args); - factory.inform(loader); - TokenStream stream = factory.create(tokenizer); - assertTokenStreamContents(stream, new String[] { "avion" }); - } - - /** - * Test creating an elision filter without specifying any articles - */ - public void testDefaultArticles() throws Exception { - Reader reader = new StringReader("l'avion"); - Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false); - ElisionFilterFactory factory = new ElisionFilterFactory(); - factory.setLuceneMatchVersion(TEST_VERSION_CURRENT); - Map args = Collections.emptyMap(); - factory.init(args); - ResourceLoader loader = new ResourceAsStreamResourceLoader(getClass()); - factory.inform(loader); - TokenStream stream = factory.create(tokenizer); - assertTokenStreamContents(stream, new String[] { "avion" }); - } - - /** - * Test setting ignoreCase=true - */ - public void testCaseInsensitive() throws Exception { - Reader reader = new StringReader("L'avion"); - Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false); - ElisionFilterFactory factory = new ElisionFilterFactory(); - factory.setLuceneMatchVersion(TEST_VERSION_CURRENT); - ResourceLoader loader = new ResourceAsStreamResourceLoader(getClass()); - Map args = new HashMap(); - args.put("articles", "frenchArticles.txt"); - args.put("ignoreCase", "true"); - factory.init(args); - factory.inform(loader); - TokenStream stream = factory.create(tokenizer); - assertTokenStreamContents(stream, new String[] { "avion" }); - } - -} Index: lucene/analysis/common/src/java/org/apache/lucene/analysis/util/ElisionFilterFactory.java =================================================================== --- lucene/analysis/common/src/java/org/apache/lucene/analysis/util/ElisionFilterFactory.java (working copy) +++ lucene/analysis/common/src/java/org/apache/lucene/analysis/util/ElisionFilterFactory.java (working copy) @@ -1,4 +1,4 @@ -package org.apache.lucene.analysis.fr; +package org.apache.lucene.analysis.util; /* * Licensed to the Apache Software Foundation (ASF) under one or more @@ -17,10 +17,9 @@ * limitations under the License. */ -import org.apache.lucene.analysis.util.*; - import java.io.IOException; import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.fr.FrenchAnalyzer; /** * Factory for {@link ElisionFilter}. @@ -46,12 +45,13 @@ if (articlesFile != null) { articles = getWordSet(loader, articlesFile, ignoreCase); } + if (articles == null) { + articles = FrenchAnalyzer.DEFAULT_ARTICLES; + } } public ElisionFilter create(TokenStream input) { - assureMatchVersion(); - return articles == null ? new ElisionFilter(luceneMatchVersion,input) : - new ElisionFilter(luceneMatchVersion,input,articles); + return new ElisionFilter(input, articles); } } Index: lucene/analysis/common/src/java/org/apache/lucene/analysis/util/ElisionFilter.java =================================================================== --- lucene/analysis/common/src/java/org/apache/lucene/analysis/util/ElisionFilter.java (working copy) +++ lucene/analysis/common/src/java/org/apache/lucene/analysis/util/ElisionFilter.java (working copy) @@ -1,4 +1,4 @@ -package org.apache.lucene.analysis.fr; +package org.apache.lucene.analysis.util; /* * Licensed to the Apache Software Foundation (ASF) under one or more @@ -18,13 +18,11 @@ */ import java.io.IOException; -import java.util.Arrays; import org.apache.lucene.analysis.TokenFilter; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; import org.apache.lucene.analysis.util.CharArraySet; -import org.apache.lucene.util.Version; /** * Removes elisions from a {@link TokenStream}. For example, "l'avion" (the plane) will be @@ -33,31 +31,17 @@ * @see Elision in Wikipedia */ public final class ElisionFilter extends TokenFilter { - private CharArraySet articles = CharArraySet.EMPTY_SET; + private final CharArraySet articles; private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class); - private static final CharArraySet DEFAULT_ARTICLES = CharArraySet.unmodifiableSet( - new CharArraySet(Version.LUCENE_CURRENT, Arrays.asList( - "l", "m", "t", "qu", "n", "s", "j"), true)); - private static char[] apostrophes = {'\'', '\u2019'}; - /** - * Constructs an elision filter with standard stop words - */ - public ElisionFilter(Version matchVersion, TokenStream input) { - this(matchVersion, input, DEFAULT_ARTICLES); - } - - /** * Constructs an elision filter with a Set of stop words - * @param matchVersion the lucene backwards compatibility version * @param input the source {@link TokenStream} * @param articles a set of stopword articles */ - public ElisionFilter(Version matchVersion, TokenStream input, CharArraySet articles) { + public ElisionFilter(TokenStream input, CharArraySet articles) { super(input); - this.articles = CharArraySet.unmodifiableSet( - new CharArraySet(matchVersion, articles, true)); + this.articles = articles; } /** @@ -69,22 +53,18 @@ char[] termBuffer = termAtt.buffer(); int termLength = termAtt.length(); - int minPoz = Integer.MAX_VALUE; - for (int i = 0; i < apostrophes.length; i++) { - char apos = apostrophes[i]; - // The equivalent of String.indexOf(ch) - for (int poz = 0; poz < termLength ; poz++) { - if (termBuffer[poz] == apos) { - minPoz = Math.min(poz, minPoz); - break; - } + int index = -1; + for (int i = 0; i < termLength; i++) { + char ch = termBuffer[i]; + if (ch == '\'' || ch == '\u2019') { + index = i; + break; } } // An apostrophe has been found. If the prefix is an article strip it off. - if (minPoz != Integer.MAX_VALUE - && articles.contains(termAtt.buffer(), 0, minPoz)) { - termAtt.copyBuffer(termAtt.buffer(), minPoz + 1, termAtt.length() - (minPoz + 1)); + if (index >= 0 && articles.contains(termBuffer, 0, index)) { + termAtt.copyBuffer(termBuffer, index + 1, termLength - (index + 1)); } return true; Index: lucene/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java =================================================================== --- lucene/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java (revision 1366186) +++ lucene/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java (working copy) @@ -24,7 +24,6 @@ import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.core.LowerCaseFilter; import org.apache.lucene.analysis.core.StopFilter; -import org.apache.lucene.analysis.fr.ElisionFilter; import org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.Tokenizer; @@ -32,6 +31,7 @@ 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.ElisionFilter; import org.apache.lucene.analysis.util.StopwordAnalyzerBase; import org.apache.lucene.analysis.util.WordlistLoader; import org.apache.lucene.util.IOUtils; @@ -129,7 +129,7 @@ Reader reader) { final Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); - result = new ElisionFilter(matchVersion, result, DEFAULT_ARTICLES); + result = new ElisionFilter(result, DEFAULT_ARTICLES); result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stopwords); if(!stemExclusionSet.isEmpty()) Index: lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java =================================================================== --- lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java (revision 1366186) +++ lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java (working copy) @@ -1,95 +0,0 @@ -package org.apache.lucene.analysis.fr; - -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import java.io.IOException; -import java.util.Arrays; - -import org.apache.lucene.analysis.TokenFilter; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; -import org.apache.lucene.analysis.util.CharArraySet; -import org.apache.lucene.util.Version; - -/** - * Removes elisions from a {@link TokenStream}. For example, "l'avion" (the plane) will be - * tokenized as "avion" (plane). - * - * @see Elision in Wikipedia - */ -public final class ElisionFilter extends TokenFilter { - private CharArraySet articles = CharArraySet.EMPTY_SET; - private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class); - private static final CharArraySet DEFAULT_ARTICLES = CharArraySet.unmodifiableSet( - new CharArraySet(Version.LUCENE_CURRENT, Arrays.asList( - "l", "m", "t", "qu", "n", "s", "j"), true)); - - private static char[] apostrophes = {'\'', '\u2019'}; - - /** - * Constructs an elision filter with standard stop words - */ - public ElisionFilter(Version matchVersion, TokenStream input) { - this(matchVersion, input, DEFAULT_ARTICLES); - } - - /** - * Constructs an elision filter with a Set of stop words - * @param matchVersion the lucene backwards compatibility version - * @param input the source {@link TokenStream} - * @param articles a set of stopword articles - */ - public ElisionFilter(Version matchVersion, TokenStream input, CharArraySet articles) { - super(input); - this.articles = CharArraySet.unmodifiableSet( - new CharArraySet(matchVersion, articles, true)); - } - - /** - * Increments the {@link TokenStream} with a {@link CharTermAttribute} without elisioned start - */ - @Override - public final boolean incrementToken() throws IOException { - if (input.incrementToken()) { - char[] termBuffer = termAtt.buffer(); - int termLength = termAtt.length(); - - int minPoz = Integer.MAX_VALUE; - for (int i = 0; i < apostrophes.length; i++) { - char apos = apostrophes[i]; - // The equivalent of String.indexOf(ch) - for (int poz = 0; poz < termLength ; poz++) { - if (termBuffer[poz] == apos) { - minPoz = Math.min(poz, minPoz); - break; - } - } - } - - // An apostrophe has been found. If the prefix is an article strip it off. - if (minPoz != Integer.MAX_VALUE - && articles.contains(termAtt.buffer(), 0, minPoz)) { - termAtt.copyBuffer(termAtt.buffer(), minPoz + 1, termAtt.length() - (minPoz + 1)); - } - - return true; - } else { - return false; - } - } -} Index: lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java =================================================================== --- lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java (revision 1366186) +++ lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java (working copy) @@ -28,6 +28,7 @@ import org.apache.lucene.analysis.standard.StandardTokenizer; import org.apache.lucene.analysis.standard.StandardAnalyzer; // for javadoc import org.apache.lucene.analysis.util.CharArraySet; +import org.apache.lucene.analysis.util.ElisionFilter; import org.apache.lucene.analysis.util.StopwordAnalyzerBase; import org.apache.lucene.analysis.util.WordlistLoader; import org.apache.lucene.util.IOUtils; @@ -35,6 +36,7 @@ import java.io.IOException; import java.io.Reader; +import java.util.Arrays; /** * {@link Analyzer} for French language. @@ -54,6 +56,11 @@ /** File containing default French stopwords. */ public final static String DEFAULT_STOPWORD_FILE = "french_stop.txt"; + /** Default set of articles for ElisionFilter */ + public static final CharArraySet DEFAULT_ARTICLES = CharArraySet.unmodifiableSet( + new CharArraySet(Version.LUCENE_CURRENT, Arrays.asList( + "l", "m", "t", "qu", "n", "s", "j"), true)); + /** * Contains words that should be indexed but not stemmed. */ @@ -134,7 +141,7 @@ Reader reader) { final Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); - result = new ElisionFilter(matchVersion, result); + result = new ElisionFilter(result, DEFAULT_ARTICLES); result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stopwords); if(!excltable.isEmpty()) Index: lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilterFactory.java =================================================================== --- lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilterFactory.java (revision 1366186) +++ lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilterFactory.java (working copy) @@ -1,57 +0,0 @@ -package org.apache.lucene.analysis.fr; - -/* - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import org.apache.lucene.analysis.util.*; - -import java.io.IOException; -import org.apache.lucene.analysis.TokenStream; - -/** - * Factory for {@link ElisionFilter}. - * 
- * <fieldType name="text_elsn" class="solr.TextField" positionIncrementGap="100">
- *   <analyzer>
- *     <tokenizer class="solr.StandardTokenizerFactory"/>
- *     <filter class="solr.LowerCaseFilterFactory"/>
- *     <filter class="solr.ElisionFilterFactory" 
- *       articles="stopwordarticles.txt" ignoreCase="true"/>
- *   </analyzer>
- * </fieldType>
- * - */ -public class ElisionFilterFactory extends TokenFilterFactory implements ResourceLoaderAware { - - private CharArraySet articles; - - public void inform(ResourceLoader loader) throws IOException { - String articlesFile = args.get("articles"); - boolean ignoreCase = getBoolean("ignoreCase", false); - - if (articlesFile != null) { - articles = getWordSet(loader, articlesFile, ignoreCase); - } - } - - public ElisionFilter create(TokenStream input) { - assureMatchVersion(); - return articles == null ? new ElisionFilter(luceneMatchVersion,input) : - new ElisionFilter(luceneMatchVersion,input,articles); - } -} - Index: lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java =================================================================== --- lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java (revision 1366186) +++ lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java (working copy) @@ -24,7 +24,6 @@ import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.core.LowerCaseFilter; import org.apache.lucene.analysis.core.StopFilter; -import org.apache.lucene.analysis.fr.ElisionFilter; import org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.Tokenizer; @@ -32,6 +31,7 @@ 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.ElisionFilter; import org.apache.lucene.analysis.util.StopwordAnalyzerBase; import org.apache.lucene.util.Version; import org.tartarus.snowball.ext.CatalanStemmer; @@ -127,7 +127,7 @@ Reader reader) { final Tokenizer source = new StandardTokenizer(matchVersion, reader); TokenStream result = new StandardFilter(matchVersion, source); - result = new ElisionFilter(matchVersion, result, DEFAULT_ARTICLES); + result = new ElisionFilter(result, DEFAULT_ARTICLES); result = new LowerCaseFilter(matchVersion, result); result = new StopFilter(matchVersion, result, stopwords); if(!stemExclusionSet.isEmpty()) Index: lucene/analysis/common/src/java/org/apache/lucene/analysis/ga/IrishAnalyzer.java =================================================================== --- lucene/analysis/common/src/java/org/apache/lucene/analysis/ga/IrishAnalyzer.java (revision 1366186) +++ lucene/analysis/common/src/java/org/apache/lucene/analysis/ga/IrishAnalyzer.java (working copy) @@ -23,7 +23,6 @@ import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.core.StopFilter; -import org.apache.lucene.analysis.fr.ElisionFilter; import org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.Tokenizer; @@ -31,6 +30,7 @@ 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.ElisionFilter; import org.apache.lucene.analysis.util.StopwordAnalyzerBase; import org.apache.lucene.util.Version; import org.tartarus.snowball.ext.IrishStemmer; @@ -140,7 +140,7 @@ StopFilter s = new StopFilter(matchVersion, result, HYPHENATIONS); s.setEnablePositionIncrements(false); result = s; - result = new ElisionFilter(matchVersion, result, DEFAULT_ARTICLES); + result = new ElisionFilter(result, DEFAULT_ARTICLES); result = new IrishLowerCaseFilter(result); result = new StopFilter(matchVersion, result, stopwords); if(!stemExclusionSet.isEmpty()) Index: lucene/analysis/common/src/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory =================================================================== --- lucene/analysis/common/src/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory (revision 1366186) +++ lucene/analysis/common/src/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory (working copy) @@ -40,7 +40,6 @@ org.apache.lucene.analysis.es.SpanishLightStemFilterFactory org.apache.lucene.analysis.fa.PersianNormalizationFilterFactory org.apache.lucene.analysis.fi.FinnishLightStemFilterFactory -org.apache.lucene.analysis.fr.ElisionFilterFactory org.apache.lucene.analysis.fr.FrenchLightStemFilterFactory org.apache.lucene.analysis.fr.FrenchMinimalStemFilterFactory org.apache.lucene.analysis.ga.IrishLowerCaseFilterFactory @@ -88,3 +87,4 @@ org.apache.lucene.analysis.synonym.SynonymFilterFactory org.apache.lucene.analysis.th.ThaiWordFilterFactory org.apache.lucene.analysis.tr.TurkishLowerCaseFilterFactory +org.apache.lucene.analysis.util.ElisionFilterFactory