Search in sources :

Example 21 with KeywordTokenizer

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

the class TestASCIIFoldingFilter method testEmptyTerm.

public void testEmptyTerm() throws IOException {
    Analyzer a = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer tokenizer = new KeywordTokenizer();
            return new TokenStreamComponents(tokenizer, new ASCIIFoldingFilter(tokenizer, random().nextBoolean()));
        }
    };
    checkOneTerm(a, "", "");
    a.close();
}
Also used : Analyzer(org.apache.lucene.analysis.Analyzer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer) Tokenizer(org.apache.lucene.analysis.Tokenizer) MockTokenizer(org.apache.lucene.analysis.MockTokenizer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer)

Example 22 with KeywordTokenizer

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

the class TestSynonymMapFilter method testEmptyTerm.

public void testEmptyTerm() throws IOException {
    Random random = random();
    final int numIters = atLeast(10);
    for (int i = 0; i < numIters; i++) {
        b = new SynonymMap.Builder(random.nextBoolean());
        final int numEntries = atLeast(10);
        for (int j = 0; j < numEntries; j++) {
            add(randomNonEmptyString(), randomNonEmptyString(), random.nextBoolean());
        }
        final SynonymMap map = b.build();
        final boolean ignoreCase = random.nextBoolean();
        final Analyzer analyzer = new Analyzer() {

            @Override
            protected TokenStreamComponents createComponents(String fieldName) {
                Tokenizer tokenizer = new KeywordTokenizer();
                return new TokenStreamComponents(tokenizer, new SynonymFilter(tokenizer, map, ignoreCase));
            }
        };
        checkAnalysisConsistency(random, analyzer, random.nextBoolean(), "");
        analyzer.close();
    }
}
Also used : Random(java.util.Random) Analyzer(org.apache.lucene.analysis.Analyzer) MockAnalyzer(org.apache.lucene.analysis.MockAnalyzer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer) Tokenizer(org.apache.lucene.analysis.Tokenizer) MockTokenizer(org.apache.lucene.analysis.MockTokenizer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer)

Example 23 with KeywordTokenizer

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

the class TestGermanStemFilter method testEmptyTerm.

public void testEmptyTerm() throws IOException {
    Analyzer a = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer tokenizer = new KeywordTokenizer();
            return new TokenStreamComponents(tokenizer, new GermanStemFilter(tokenizer));
        }
    };
    checkOneTerm(a, "", "");
    a.close();
}
Also used : Analyzer(org.apache.lucene.analysis.Analyzer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer) Tokenizer(org.apache.lucene.analysis.Tokenizer) MockTokenizer(org.apache.lucene.analysis.MockTokenizer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer)

Example 24 with KeywordTokenizer

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

the class TestFrenchLightStemFilter method testEmptyTerm.

public void testEmptyTerm() throws IOException {
    Analyzer a = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer tokenizer = new KeywordTokenizer();
            return new TokenStreamComponents(tokenizer, new FrenchLightStemFilter(tokenizer));
        }
    };
    checkOneTerm(a, "", "");
    a.close();
}
Also used : Analyzer(org.apache.lucene.analysis.Analyzer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer) Tokenizer(org.apache.lucene.analysis.Tokenizer) MockTokenizer(org.apache.lucene.analysis.MockTokenizer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer)

Example 25 with KeywordTokenizer

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

the class TestFrenchMinimalStemFilter method testEmptyTerm.

public void testEmptyTerm() throws IOException {
    Analyzer a = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer tokenizer = new KeywordTokenizer();
            return new TokenStreamComponents(tokenizer, new FrenchMinimalStemFilter(tokenizer));
        }
    };
    checkOneTerm(a, "", "");
    a.close();
}
Also used : Analyzer(org.apache.lucene.analysis.Analyzer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer) Tokenizer(org.apache.lucene.analysis.Tokenizer) MockTokenizer(org.apache.lucene.analysis.MockTokenizer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer)

Aggregations

KeywordTokenizer (org.apache.lucene.analysis.core.KeywordTokenizer)95 Tokenizer (org.apache.lucene.analysis.Tokenizer)86 Analyzer (org.apache.lucene.analysis.Analyzer)75 MockTokenizer (org.apache.lucene.analysis.MockTokenizer)64 TokenStream (org.apache.lucene.analysis.TokenStream)14 StringReader (java.io.StringReader)11 WhitespaceTokenizer (org.apache.lucene.analysis.core.WhitespaceTokenizer)11 LowerCaseFilter (org.apache.lucene.analysis.core.LowerCaseFilter)4 PorterStemFilter (org.apache.lucene.analysis.en.PorterStemFilter)4 Random (java.util.Random)3 CharArraySet (org.apache.lucene.analysis.CharArraySet)3 LetterTokenizer (org.apache.lucene.analysis.core.LetterTokenizer)3 StandardAnalyzer (org.apache.lucene.analysis.standard.StandardAnalyzer)3 StandardTokenizer (org.apache.lucene.analysis.standard.StandardTokenizer)3 CharTermAttribute (org.apache.lucene.analysis.tokenattributes.CharTermAttribute)3 Transliterator (com.ibm.icu.text.Transliterator)2 UnicodeSet (com.ibm.icu.text.UnicodeSet)2 MockAnalyzer (org.apache.lucene.analysis.MockAnalyzer)2 LowerCaseTokenizer (org.apache.lucene.analysis.core.LowerCaseTokenizer)2 RemoveDuplicatesTokenFilter (org.apache.lucene.analysis.miscellaneous.RemoveDuplicatesTokenFilter)2