Examples with CharArraySet org.apache.lucene.analysis.CharArraySet used on opensource projects

Example 61 with CharArraySet

use of org.apache.lucene.analysis.CharArraySet in project lucene-solr by apache.

the class TestCharArraySet method testContainsWithNull.

/**
   * Test for NPE
   */
public void testContainsWithNull() {
    CharArraySet set = new CharArraySet(1, true);
    expectThrows(NullPointerException.class, () -> {
        set.contains((char[]) null, 0, 10);
    });
    expectThrows(NullPointerException.class, () -> {
        set.contains((CharSequence) null);
    });
    expectThrows(NullPointerException.class, () -> {
        set.contains((Object) null);
    });
}

Example 62 with CharArraySet

use of org.apache.lucene.analysis.CharArraySet in project lucene-solr by apache.

the class TestCommonGramsFilterFactory method testInform.

public void testInform() throws Exception {
    ResourceLoader loader = new ClasspathResourceLoader(TestStopFilterFactory.class);
    assertTrue("loader is null and it shouldn't be", loader != null);
    CommonGramsFilterFactory factory = (CommonGramsFilterFactory) tokenFilterFactory("CommonGrams", Version.LATEST, loader, "words", "stop-1.txt", "ignoreCase", "true");
    CharArraySet words = factory.getCommonWords();
    assertTrue("words is null and it shouldn't be", words != null);
    assertTrue("words Size: " + words.size() + " is not: " + 2, words.size() == 2);
    assertTrue(factory.isIgnoreCase() + " does not equal: " + true, factory.isIgnoreCase() == true);
    factory = (CommonGramsFilterFactory) tokenFilterFactory("CommonGrams", Version.LATEST, loader, "words", "stop-1.txt, stop-2.txt", "ignoreCase", "true");
    words = factory.getCommonWords();
    assertTrue("words is null and it shouldn't be", words != null);
    assertTrue("words Size: " + words.size() + " is not: " + 4, words.size() == 4);
    assertTrue(factory.isIgnoreCase() + " does not equal: " + true, factory.isIgnoreCase() == true);
    factory = (CommonGramsFilterFactory) tokenFilterFactory("CommonGrams", Version.LATEST, loader, "words", "stop-snowball.txt", "format", "snowball", "ignoreCase", "true");
    words = factory.getCommonWords();
    assertEquals(8, words.size());
    assertTrue(words.contains("he"));
    assertTrue(words.contains("him"));
    assertTrue(words.contains("his"));
    assertTrue(words.contains("himself"));
    assertTrue(words.contains("she"));
    assertTrue(words.contains("her"));
    assertTrue(words.contains("hers"));
    assertTrue(words.contains("herself"));
}

Example 63 with CharArraySet

use of org.apache.lucene.analysis.CharArraySet in project lucene-solr by apache.

the class TestCommonGramsQueryFilterFactory method testDefaults.

/**
   * If no words are provided, then a set of english default stopwords is used.
   */
public void testDefaults() throws Exception {
    CommonGramsQueryFilterFactory factory = (CommonGramsQueryFilterFactory) tokenFilterFactory("CommonGramsQuery");
    CharArraySet words = factory.getCommonWords();
    assertTrue("words is null and it shouldn't be", words != null);
    assertTrue(words.contains("the"));
    Tokenizer tokenizer = whitespaceMockTokenizer("testing the factory");
    TokenStream stream = factory.create(tokenizer);
    assertTokenStreamContents(stream, new String[] { "testing_the", "the_factory" });
}

Example 64 with CharArraySet

use of org.apache.lucene.analysis.CharArraySet in project lucene-solr by apache.

the class TestCommonGramsQueryFilterFactory method testInform.

public void testInform() throws Exception {
    ResourceLoader loader = new ClasspathResourceLoader(TestStopFilterFactory.class);
    assertTrue("loader is null and it shouldn't be", loader != null);
    CommonGramsQueryFilterFactory factory = (CommonGramsQueryFilterFactory) tokenFilterFactory("CommonGramsQuery", Version.LATEST, loader, "words", "stop-1.txt", "ignoreCase", "true");
    CharArraySet words = factory.getCommonWords();
    assertTrue("words is null and it shouldn't be", words != null);
    assertTrue("words Size: " + words.size() + " is not: " + 2, words.size() == 2);
    assertTrue(factory.isIgnoreCase() + " does not equal: " + true, factory.isIgnoreCase() == true);
    factory = (CommonGramsQueryFilterFactory) tokenFilterFactory("CommonGramsQuery", Version.LATEST, loader, "words", "stop-1.txt, stop-2.txt", "ignoreCase", "true");
    words = factory.getCommonWords();
    assertTrue("words is null and it shouldn't be", words != null);
    assertTrue("words Size: " + words.size() + " is not: " + 4, words.size() == 4);
    assertTrue(factory.isIgnoreCase() + " does not equal: " + true, factory.isIgnoreCase() == true);
    factory = (CommonGramsQueryFilterFactory) tokenFilterFactory("CommonGramsQuery", Version.LATEST, loader, "words", "stop-snowball.txt", "format", "snowball", "ignoreCase", "true");
    words = factory.getCommonWords();
    assertEquals(8, words.size());
    assertTrue(words.contains("he"));
    assertTrue(words.contains("him"));
    assertTrue(words.contains("his"));
    assertTrue(words.contains("himself"));
    assertTrue(words.contains("she"));
    assertTrue(words.contains("her"));
    assertTrue(words.contains("hers"));
    assertTrue(words.contains("herself"));
}

Example 65 with CharArraySet

use of org.apache.lucene.analysis.CharArraySet in project lucene-solr by apache.

the class TestCompoundWordTokenFilter method testDumbCompoundWordsSELongestMatch.

public void testDumbCompoundWordsSELongestMatch() throws Exception {
    CharArraySet dict = makeDictionary("Bil", "Dörr", "Motor", "Tak", "Borr", "Slag", "Hammar", "Pelar", "Glas", "Ögon", "Fodral", "Bas", "Fiols", "Makare", "Gesäll", "Sko", "Vind", "Rute", "Torkare", "Blad", "Fiolsfodral");
    DictionaryCompoundWordTokenFilter tf = new DictionaryCompoundWordTokenFilter(whitespaceMockTokenizer("Basfiolsfodralmakaregesäll"), dict, CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE, CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE, CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE, true);
    assertTokenStreamContents(tf, new String[] { "Basfiolsfodralmakaregesäll", "Bas", "fiolsfodral", "fodral", "makare", "gesäll" }, new int[] { 0, 0, 0, 0, 0, 0 }, new int[] { 26, 26, 26, 26, 26, 26 }, new int[] { 1, 0, 0, 0, 0, 0 });
}