Index: lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikFilter.java =================================================================== --- lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikFilter.java (revision 1547448) +++ lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikFilter.java (working copy) @@ -65,7 +65,7 @@ * @param in input token stream * @param version Lucene version compatibility for lowercasing. */ - public MorfologikFilter(final TokenStream in, final Version version) { + public MorfologikFilter(final TokenStream in, final String dict, final Version version) { super(in); this.input = in; @@ -73,8 +73,8 @@ Thread me = Thread.currentThread(); ClassLoader cl = me.getContextClassLoader(); try { - me.setContextClassLoader(PolishStemmer.class.getClassLoader()); - this.stemmer = new PolishStemmer(); + me.setContextClassLoader(MorfologikLemmatizer.class.getClassLoader()); + this.stemmer = new MorfologikLemmatizer(dict); this.charUtils = CharacterUtils.getInstance(version); this.lemmaList = Collections.emptyList(); } finally { Index: lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikLemmatizer.java =================================================================== --- lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikLemmatizer.java (revision 0) +++ lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikLemmatizer.java (revision 0) @@ -0,0 +1,86 @@ +// -*- c-basic-offset: 2 -*- +package org.apache.lucene.analysis.morfologik; + +/* + * 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.util.ArrayList; +import java.util.Arrays; +import java.util.Iterator; +import java.util.List; +import morfologik.stemming.Dictionary; +import morfologik.stemming.DictionaryLookup; +import morfologik.stemming.IStemmer; +import morfologik.stemming.WordData; + +/** + * A dictionary-based stemmer for language. This stemmer requires an FSA-compiled dictionary to be present in + * classpath resources. + * + * Objects of this class are not thread safe. + * + * @see morfologik.stemming.DictionaryLookup + */ +public final class MorfologikLemmatizer implements IStemmer, Iterable { + + /** + * Dictionary lookup delegate. + */ + private final List delegate = new ArrayList(); + + /** + * This constructor is initialized with a built-in dictionary or fails with a runtime exception if the + * dictionary is not available. + * + * @param dictionary A constant specifying which dictionary to choose. See the Morfologik + * documentation for details or use the default. + */ + public MorfologikLemmatizer(String dictionary) { + delegate.add(new DictionaryLookup(Dictionary.getForLanguage(dictionary))); + } + + /** + * {@inheritDoc} + */ + @Override + public List lookup(CharSequence word) { + if (delegate.size() == 1) { + return delegate.get(0).lookup(word); + } else { + List forms = null; + for (DictionaryLookup lookup : delegate) { + forms = lookup.lookup(word); + if (forms.size() > 0) + break; + } + return forms; + } + } + + /** + * Iterates over all dictionary forms stored in this stemmer. + */ + @Override + public Iterator iterator() { + if (delegate.size() == 1) { + return delegate.get(0).iterator(); + } else { + throw new RuntimeException("No iteration over compound stemmer forms: " + + Arrays.toString(delegate.toArray())); + } + } +} Index: lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikFilterFactory.java =================================================================== --- lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikFilterFactory.java (revision 1547448) +++ lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikFilterFactory.java (working copy) @@ -35,8 +35,13 @@ * @see Morfologik web site */ public class MorfologikFilterFactory extends TokenFilterFactory { + + /** + * Dictionary resource + */ + private String dictionary; + /** Schema attribute. */ - @Deprecated public static final String DICTIONARY_SCHEMA_ATTRIBUTE = "dictionary"; /** Creates a new MorfologikFilterFactory */ @@ -44,12 +49,11 @@ super(args); // Be specific about no-longer-supported dictionary attribute. - String dictionaryName = get(args, DICTIONARY_SCHEMA_ATTRIBUTE); - if (dictionaryName != null && !dictionaryName.isEmpty()) { - throw new IllegalArgumentException("The " + DICTIONARY_SCHEMA_ATTRIBUTE + " attribute is no " - + "longer supported (Morfologik has one dictionary): " + dictionaryName); + dictionary = get(args, DICTIONARY_SCHEMA_ATTRIBUTE); + if (dictionary == null || dictionary.isEmpty()) { + throw new IllegalArgumentException("The " + DICTIONARY_SCHEMA_ATTRIBUTE + " attribute cannot be empty!"); } - + if (!args.isEmpty()) { throw new IllegalArgumentException("Unknown parameters: " + args); } @@ -57,6 +61,6 @@ @Override public TokenStream create(TokenStream ts) { - return new MorfologikFilter(ts, luceneMatchVersion); + return new MorfologikFilter(ts, dictionary, luceneMatchVersion); } } Index: lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikAnalyzer.java =================================================================== --- lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikAnalyzer.java (revision 1547448) +++ lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikAnalyzer.java (working copy) @@ -31,16 +31,19 @@ * @see Morfologik project page */ public class MorfologikAnalyzer extends Analyzer { + private final String dictionary; private final Version version; /** * Builds an analyzer with the default Morfologik's dictionary (polimorf). * - * @param version - * Lucene compatibility version + * @param version Lucene compatibility version + * @param dictionary A constant specifying which dictionary to choose. See the Morfologik + * documentation for details or use the default. */ - public MorfologikAnalyzer(final Version version) { - this.version = version; + public MorfologikAnalyzer(final Version version, final String dictionary) { + this.version = version; + this.dictionary = dictionary; } /** @@ -62,6 +65,6 @@ return new TokenStreamComponents( src, - new MorfologikFilter(new StandardFilter(this.version, src), this.version)); + new MorfologikFilter(new StandardFilter(this.version, src), this.dictionary, this.version)); } } Index: lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/morfologik/TestMorfologikAnalyzer.java =================================================================== --- lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/morfologik/TestMorfologikAnalyzer.java (revision 1547448) +++ lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/morfologik/TestMorfologikAnalyzer.java (working copy) @@ -38,7 +38,7 @@ public class TestMorfologikAnalyzer extends BaseTokenStreamTestCase { private Analyzer getTestAnalyzer() { - return new MorfologikAnalyzer(TEST_VERSION_CURRENT); + return new MorfologikAnalyzer(TEST_VERSION_CURRENT, "pl"); } /** Test stemming of single tokens with Morfologik library. */ @@ -168,8 +168,9 @@ /** */ public final void testKeywordAttrTokens() throws IOException { final Version version = TEST_VERSION_CURRENT; + final String dictionary = "pl"; - Analyzer a = new MorfologikAnalyzer(version) { + Analyzer a = new MorfologikAnalyzer(version, dictionary) { @Override protected TokenStreamComponents createComponents(String field, Reader reader) { final CharArraySet keywords = new CharArraySet(version, 1, false); @@ -178,7 +179,7 @@ final Tokenizer src = new StandardTokenizer(TEST_VERSION_CURRENT, reader); TokenStream result = new StandardFilter(TEST_VERSION_CURRENT, src); result = new SetKeywordMarkerFilter(result, keywords); - result = new MorfologikFilter(result, TEST_VERSION_CURRENT); + result = new MorfologikFilter(result, dictionary, TEST_VERSION_CURRENT); return new TokenStreamComponents(src, result); } Index: lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/morfologik/TestMorfologikFilterFactory.java =================================================================== --- lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/morfologik/TestMorfologikFilterFactory.java (revision 1547448) +++ lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/morfologik/TestMorfologikFilterFactory.java (working copy) @@ -20,6 +20,7 @@ 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; @@ -31,7 +32,8 @@ public class TestMorfologikFilterFactory extends BaseTokenStreamTestCase { public void testCreateDictionary() throws Exception { StringReader reader = new StringReader("rowery bilety"); - MorfologikFilterFactory factory = new MorfologikFilterFactory(Collections.emptyMap()); + Map args = new HashMap(Collections.singletonMap("dictionary", "pl")); + MorfologikFilterFactory factory = new MorfologikFilterFactory(args); TokenStream stream = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false); stream = factory.create(stream); assertTokenStreamContents(stream, new String[] {"rower", "bilet"}); @@ -41,6 +43,7 @@ public void testBogusArguments() throws Exception { try { new MorfologikFilterFactory(new HashMap() {{ + put("dictionary", "pl"); put("bogusArg", "bogusValue"); }}); fail();