Search in sources :

Example 11 with KeywordTokenizer

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

the class TestCzechStemmer 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 CzechStemFilter(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 12 with KeywordTokenizer

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

the class TestSnowballVocab method assertCorrectOutput.

/**
   * For the supplied language, run the stemmer against all strings in voc.txt
   * The output should be the same as the string in output.txt
   */
private void assertCorrectOutput(final String snowballLanguage, String dataDirectory) throws IOException {
    if (VERBOSE)
        System.out.println("checking snowball language: " + snowballLanguage);
    Analyzer a = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer t = new KeywordTokenizer();
            return new TokenStreamComponents(t, new SnowballFilter(t, snowballLanguage));
        }
    };
    assertVocabulary(a, getDataPath("TestSnowballVocabData.zip"), dataDirectory + "/voc.txt", dataDirectory + "/output.txt");
    a.close();
}
Also used : Analyzer(org.apache.lucene.analysis.Analyzer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer) Tokenizer(org.apache.lucene.analysis.Tokenizer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer)

Example 13 with KeywordTokenizer

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

the class TestSerbianNormalizationFilter 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 SerbianNormalizationFilter(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 14 with KeywordTokenizer

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

the class ShingleFilterTest 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 ShingleFilter(tokenizer));
        }
    };
    checkOneTerm(a, "", "");
    a.close();
}
Also used : Analyzer(org.apache.lucene.analysis.Analyzer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer) WhitespaceTokenizer(org.apache.lucene.analysis.core.WhitespaceTokenizer) Tokenizer(org.apache.lucene.analysis.Tokenizer) MockTokenizer(org.apache.lucene.analysis.MockTokenizer) KeywordTokenizer(org.apache.lucene.analysis.core.KeywordTokenizer)

Example 15 with KeywordTokenizer

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

the class TestHindiStemmer 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 HindiStemFilter(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) 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