LUCENE-10095: Nepali Analyzer (#290)

Add Nepali analyzer based on snowball stemmer and NLTK stopwords

lucene/CHANGES.txt

@@ -15,6 +15,10 @@ New Features
 
 * LUCENE-9589: Swedish Minimal Stemmer (janhoy)
 
+* LUCENE-9313: Add SerbianAnalyzer based on the snowball stemmer. (Dragan Ivanovic)
+
+* LUCENE-10095: Add NepaliAnalyzer based on the snowball stemmer. (Robert Muir)
+
 System Requirements
 
 * LUCENE-8738: Move to Java 11 as minimum Java version.
@@ -217,8 +221,6 @@ Improvements
   with doc values and points. In this case, there is an assumption that the same data is
   stored in these points and doc values (Mayya Sharipova, Jim Ferenczi, Adrien Grand)
 
-* LUCENE-9313: Add SerbianAnalyzer based on the snowball stemmer. (Dragan Ivanovic)
-
 * LUCENE-9449: Enhance DocComparator to provide an iterator over competitive
   documents when searching with "after". This iterator can quickly position
   on the desired "after" document skipping all documents and segments before

lucene/analysis/common/src/java/org/apache/lucene/analysis/ne/NepaliAnalyzer.java

@@ -0,0 +1,134 @@
+/*
+ * 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.
+ */
+package org.apache.lucene.analysis.ne;
+
+import java.io.IOException;
+import java.io.Reader;
+import java.io.UncheckedIOException;
+import org.apache.lucene.analysis.CharArraySet;
+import org.apache.lucene.analysis.LowerCaseFilter;
+import org.apache.lucene.analysis.StopFilter;
+import org.apache.lucene.analysis.StopwordAnalyzerBase;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.core.DecimalDigitFilter;
+import org.apache.lucene.analysis.in.IndicNormalizationFilter;
+import org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter;
+import org.apache.lucene.analysis.snowball.SnowballFilter;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.tartarus.snowball.ext.NepaliStemmer;
+
+/**
+ * Analyzer for Nepali.
+ *
+ * @since 9.0
+ */
+public final class NepaliAnalyzer extends StopwordAnalyzerBase {
+  private final CharArraySet stemExclusionSet;
+
+  /**
+   * File containing default Nepali stopwords.
+   *
+   * <p>Default stopword list is from the Apache2 python project NLTK:
+   * https://github.com/nltk/nltk_data
+   */
+  public static final String DEFAULT_STOPWORD_FILE = "stopwords.txt";
+
+  private static final String STOPWORDS_COMMENT = "#";
+
+  /**
+   * Returns an unmodifiable instance of the default stop-words set.
+   *
+   * @return an unmodifiable instance of the default stop-words set.
+   */
+  public static CharArraySet getDefaultStopSet() {
+    return DefaultSetHolder.DEFAULT_STOP_SET;
+  }
+
+  /**
+   * Atomically loads the DEFAULT_STOP_SET in a lazy fashion once the outer class accesses the
+   * static final set the first time.;
+   */
+  private static class DefaultSetHolder {
+    static final CharArraySet DEFAULT_STOP_SET;
+
+    static {
+      try {
+        DEFAULT_STOP_SET =
+            loadStopwordSet(false, NepaliAnalyzer.class, DEFAULT_STOPWORD_FILE, STOPWORDS_COMMENT);
+      } catch (IOException ex) {
+        // default set should always be present as it is part of the
+        // distribution (JAR)
+        throw new UncheckedIOException("Unable to load default stopword set", ex);
+      }
+    }
+  }
+
+  /**
+   * Builds an analyzer with the given stop words
+   *
+   * @param stopwords a stopword set
+   * @param stemExclusionSet a stemming exclusion set
+   */
+  public NepaliAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+    super(stopwords);
+    this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
+  }
+
+  /**
+   * Builds an analyzer with the given stop words
+   *
+   * @param stopwords a stopword set
+   */
+  public NepaliAnalyzer(CharArraySet stopwords) {
+    this(stopwords, CharArraySet.EMPTY_SET);
+  }
+
+  /** Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}. */
+  public NepaliAnalyzer() {
+    this(DefaultSetHolder.DEFAULT_STOP_SET);
+  }
+
+  /**
+   * Creates {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} used to tokenize all
+   * the text in the provided {@link Reader}.
+   *
+   * @return {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents} built from a {@link
+   *     StandardTokenizer} filtered with {@link LowerCaseFilter}, {@link DecimalDigitFilter},
+   *     {@link IndicNormalizationFilter}, {@link SetKeywordMarkerFilter} if a stem exclusion set is
+   *     provided, {@link SnowballFilter}, and Nepali Stop words
+   */
+  @Override
+  protected TokenStreamComponents createComponents(String fieldName) {
+    final Tokenizer source = new StandardTokenizer();
+    TokenStream result = new LowerCaseFilter(source);
+    result = new DecimalDigitFilter(result);
+    if (!stemExclusionSet.isEmpty()) result = new SetKeywordMarkerFilter(result, stemExclusionSet);
+    result = new IndicNormalizationFilter(result);
+    result = new StopFilter(result, stopwords);
+    result = new SnowballFilter(result, new NepaliStemmer());
+    return new TokenStreamComponents(source, result);
+  }
+
+  @Override
+  protected TokenStream normalize(String fieldName, TokenStream in) {
+    TokenStream result = new LowerCaseFilter(in);
+    result = new DecimalDigitFilter(result);
+    result = new IndicNormalizationFilter(result);
+    return result;
+  }
+}

lucene/analysis/common/src/java/org/apache/lucene/analysis/ne/package-info.java

@@ -0,0 +1,19 @@
+/*
+ * 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.
+ */
+
+/** Analyzer for Nepali. */
+package org.apache.lucene.analysis.ne;

lucene/analysis/common/src/resources/org/apache/lucene/analysis/ne/stopwords.txt

@@ -0,0 +1,256 @@
+# nepali stopwords from https://github.com/nltk/nltk_data
+छ
+र
+पनि
+छन्
+लागि
+भएको
+गरेको
+भने
+गर्न
+गर्ने
+हो
+तथा
+यो
+रहेको
+उनले
+थियो
+हुने
+गरेका
+थिए
+गर्दै
+तर
+नै
+को
+मा
+हुन्
+भन्ने
+हुन
+गरी
+त
+हुन्छ
+अब
+के
+रहेका
+गरेर
+छैन
+दिए
+भए
+यस
+ले
+गर्नु
+औं
+सो
+त्यो
+कि
+जुन
+यी
+का
+गरि
+ती
+न
+छु
+छौं
+लाई
+नि
+उप
+अक्सर
+आदि
+कसरी
+क्रमशः
+चाले
+अगाडी
+अझै
+अनुसार
+अन्तर्गत
+अन्य
+अन्यत्र
+अन्यथा
+अरु
+अरुलाई
+अर्को
+अर्थात
+अर्थात्
+अलग
+आए
+आजको
+ओठ
+आत्म
+आफू
+आफूलाई
+आफ्नै
+आफ्नो
+आयो
+उदाहरण
+उनको
+उहालाई
+एउटै
+एक
+एकदम
+कतै
+कम से कम
+कसै
+कसैले
+कहाँबाट
+कहिलेकाहीं
+का
+किन
+किनभने
+कुनै
+कुरा
+कृपया
+केही
+कोही
+गए
+गरौं
+गर्छ
+गर्छु
+गर्नुपर्छ
+गयौ
+गैर
+चार
+चाहनुहुन्छ
+चाहन्छु
+चाहिए
+छू
+जताततै
+जब
+जबकि
+जसको
+जसबाट
+जसमा
+जसलाई
+जसले
+जस्तै
+जस्तो
+जस्तोसुकै
+जहाँ
+जान
+जाहिर
+जे
+जो
+ठीक
+तत्काल
+तदनुसार
+तपाईको
+तपाई
+पर्याप्त
+पहिले
+पहिलो
+पहिल्यै
+पाँच
+पाँचौं
+तल
+तापनी
+तिनी
+तिनीहरू
+तिनीहरुको
+तिनिहरुलाई
+तिमी
+तिर
+तीन
+तुरुन्तै
+तेस्रो
+तेस्कारण
+पूर्व
+प्रति
+प्रतेक
+प्लस
+फेरी
+बने
+त्सपछि
+त्सैले
+त्यहाँ
+थिएन
+दिनुभएको
+दिनुहुन्छ
+दुई
+देखि
+बरु
+बारे
+बाहिर
+देखिन्छ
+देखियो
+देखे
+देखेको
+देखेर
+दोस्रो
+धेरै
+नजिकै
+नत्र
+नयाँ
+निम्ति
+बाहेक
+बीच
+बीचमा
+भन
+निम्न
+निम्नानुसार
+निर्दिष्ट
+नौ
+पक्का
+पक्कै
+पछि
+पछिल्लो
+पटक
+पर्छ
+पर्थ्यो
+भन्छन्
+भन्
+भन्छु
+भन्दा
+भन्नुभयो
+भर
+भित्र
+भित्री
+म
+मलाई
+मात्र
+माथि
+मुख्य
+मेरो
+यति
+यथोचित
+यदि
+यद्यपि
+यसको
+यसपछि
+यसबाहेक
+यसरी
+यसो
+यस्तो
+यहाँ
+यहाँसम्म
+या
+रही
+राखे
+राख्छ
+राम्रो
+रूप
+लगभग
+वरीपरी
+वास्तवमा
+बिरुद्ध
+बिशेष
+सायद
+शायद
+संग
+संगै
+सक्छ
+सट्टा
+सधै
+सबै
+सबैलाई
+समय
+सम्भव
+सम्म
+सही
+साँच्चै
+सात
+साथ
+साथै
+सारा
+सोही
+स्पष्ट
+हरे
+हरेक

lucene/analysis/common/src/test/org/apache/lucene/analysis/ne/TestNepaliAnalyzer.java

@@ -0,0 +1,76 @@
+/*
+ * 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.
+ */
+package org.apache.lucene.analysis.ne;
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.BaseTokenStreamTestCase;
+import org.apache.lucene.analysis.CharArraySet;
+
+/** Tests the NepaliAnalyzer */
+public class TestNepaliAnalyzer extends BaseTokenStreamTestCase {
+  /** This test fails with NPE when the stopwords file is missing in classpath */
+  public void testResourcesAvailable() {
+    new NepaliAnalyzer().close();
+  }
+
+  /** test that snowball stemmer is hooked in correctly */
+  public void testStemming() throws Exception {
+    Analyzer a = new NepaliAnalyzer();
+    // friend
+    checkOneTerm(a, "मित्र", "मित्र");
+    // friends
+    checkOneTerm(a, "मित्रहरु", "मित्र");
+    a.close();
+  }
+
+  public void testStopwords() throws Exception {
+    Analyzer a = new NepaliAnalyzer();
+    assertAnalyzesTo(
+        a,
+        "सबै व्यक्तिहरू जन्मजात स्वतन्त्र हुन् ती सबैको समान अधिकार र महत्व",
+        new String[] {"व्यक्ति", "जन्मजात", "स्वतन्त्र", "सबै", "समान", "अधिकार", "महत्व"});
+    a.close();
+  }
+
+  /** nepali has no case, but any latin-1 etc should be casefolded */
+  public void testLowerCase() throws Exception {
+    Analyzer a = new NepaliAnalyzer();
+    checkOneTerm(a, "FIFA", "fifa");
+    a.close();
+  }
+
+  public void testExclusionSet() throws Exception {
+    CharArraySet exclusionSet = new CharArraySet(asSet("मित्रहरु"), false);
+    Analyzer a = new NepaliAnalyzer(NepaliAnalyzer.getDefaultStopSet(), exclusionSet);
+    checkOneTerm(a, "मित्रहरु", "मित्रहरु");
+    a.close();
+  }
+
+  /** test we fold digits to latin-1 */
+  public void testDigits() throws Exception {
+    NepaliAnalyzer a = new NepaliAnalyzer();
+    checkOneTerm(a, "१२३४", "1234");
+    a.close();
+  }
+
+  /** blast some random strings through the analyzer */
+  public void testRandomStrings() throws Exception {
+    Analyzer analyzer = new NepaliAnalyzer();
+    checkRandomData(random(), analyzer, 200 * RANDOM_MULTIPLIER);
+    analyzer.close();
+  }
+}