use of org.apache.commons.codec.language.Soundex in project lucene-solr by apache.
the class TestPhoneticFilter method testRandomStrings.
/** blast some random strings through the analyzer */
public void testRandomStrings() throws IOException {
Encoder[] encoders = new Encoder[] { new Metaphone(), new DoubleMetaphone(), new Soundex(), new RefinedSoundex(), new Caverphone2() };
for (final Encoder e : encoders) {
Analyzer a = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
return new TokenStreamComponents(tokenizer, new PhoneticFilter(tokenizer, e, false));
}
};
checkRandomData(random(), a, 1000 * RANDOM_MULTIPLIER);
a.close();
Analyzer b = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer tokenizer = new MockTokenizer(MockTokenizer.WHITESPACE, false);
return new TokenStreamComponents(tokenizer, new PhoneticFilter(tokenizer, e, false));
}
};
checkRandomData(random(), b, 1000 * RANDOM_MULTIPLIER);
b.close();
}
}
use of org.apache.commons.codec.language.Soundex in project lucene-solr by apache.
the class TestPhoneticFilter method testAlgorithms.
public void testAlgorithms() throws Exception {
assertAlgorithm(new Metaphone(), true, "aaa bbb ccc easgasg", new String[] { "A", "aaa", "B", "bbb", "KKK", "ccc", "ESKS", "easgasg" });
assertAlgorithm(new Metaphone(), false, "aaa bbb ccc easgasg", new String[] { "A", "B", "KKK", "ESKS" });
assertAlgorithm(new DoubleMetaphone(), true, "aaa bbb ccc easgasg", new String[] { "A", "aaa", "PP", "bbb", "KK", "ccc", "ASKS", "easgasg" });
assertAlgorithm(new DoubleMetaphone(), false, "aaa bbb ccc easgasg", new String[] { "A", "PP", "KK", "ASKS" });
assertAlgorithm(new Soundex(), true, "aaa bbb ccc easgasg", new String[] { "A000", "aaa", "B000", "bbb", "C000", "ccc", "E220", "easgasg" });
assertAlgorithm(new Soundex(), false, "aaa bbb ccc easgasg", new String[] { "A000", "B000", "C000", "E220" });
assertAlgorithm(new RefinedSoundex(), true, "aaa bbb ccc easgasg", new String[] { "A0", "aaa", "B1", "bbb", "C3", "ccc", "E034034", "easgasg" });
assertAlgorithm(new RefinedSoundex(), false, "aaa bbb ccc easgasg", new String[] { "A0", "B1", "C3", "E034034" });
assertAlgorithm(new Caverphone2(), true, "Darda Karleen Datha Carlene", new String[] { "TTA1111111", "Darda", "KLN1111111", "Karleen", "TTA1111111", "Datha", "KLN1111111", "Carlene" });
assertAlgorithm(new Caverphone2(), false, "Darda Karleen Datha Carlene", new String[] { "TTA1111111", "KLN1111111", "TTA1111111", "KLN1111111" });
assertAlgorithm(new Nysiis(), true, "aaa bbb ccc easgasg", new String[] { "A", "aaa", "B", "bbb", "C", "ccc", "EASGAS", "easgasg" });
assertAlgorithm(new Nysiis(), false, "aaa bbb ccc easgasg", new String[] { "A", "B", "C", "EASGAS" });
}
use of org.apache.commons.codec.language.Soundex in project lucene-solr by apache.
the class TestPhoneticFilter method testEmptyTerm.
public void testEmptyTerm() throws IOException {
Encoder[] encoders = new Encoder[] { new Metaphone(), new DoubleMetaphone(), new Soundex(), new RefinedSoundex(), new Caverphone2() };
for (final Encoder e : encoders) {
Analyzer a = new Analyzer() {
@Override
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer tokenizer = new KeywordTokenizer();
return new TokenStreamComponents(tokenizer, new PhoneticFilter(tokenizer, e, random().nextBoolean()));
}
};
checkOneTerm(a, "", "");
a.close();
}
}
Aggregations