Example usage for org.apache.lucene.analysis MockAnalyzer MockAnalyzer

Introduction

In this page you can find the example usage for org.apache.lucene.analysis MockAnalyzer MockAnalyzer.

Prototype

public MockAnalyzer(Random random)

Source Link

Document

Create a Whitespace-lowercasing analyzer with no stopwords removal.

Usage

From source file:brightsolid.solr.plugins.TestTargetPositionQuerySynonyms.java

License:Apache License

@Override
public void setUp() throws Exception {
    super.setUp();

    String testFile = "one, uno, un\n" + "two, dos, too\n" + "three, free, tres";

    SolrSynonymParser parser = new SolrSynonymParser(true, true, new MockAnalyzer(random()));
    parser.parse(new StringReader(testFile));

    final SynonymMap map = parser.build();
    Analyzer analyzer = new Analyzer() {
        @Override//from w  ww .  j  a va  2  s.c o  m
        protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
            Tokenizer tokenizer = new MockTokenizer(reader, MockTokenizer.WHITESPACE, true);
            return new TokenStreamComponents(tokenizer, new SynonymFilter(tokenizer, map, false));
        }
    };

    directory = newDirectory();
    RandomIndexWriter iw = new RandomIndexWriter(random(), directory, analyzer);
    Document doc = new Document();
    FieldType newType = new FieldType(org.apache.lucene.document.TextField.TYPE_STORED);
    newType.setOmitNorms(true);
    Field field = newField("field", "", newType);
    field.fieldType().setOmitNorms(true);

    doc.add(field);

    field.setStringValue("one two three");
    iw.addDocument(doc);
    field.setStringValue("two three one");
    iw.addDocument(doc);
    field.setStringValue("three one two");
    iw.addDocument(doc);

    reader = iw.getReader();
    iw.close();
    searcher = newSearcher(reader);
}

From source file:com.meizu.nlp.classification.BooleanPerceptronClassifierTest.java

License:Apache License

@Test
public void testBasicUsage() throws Exception {
    checkCorrectClassification(new BooleanPerceptronClassifier(), TECHNOLOGY_INPUT, false,
            new MockAnalyzer(random()), textFieldName, booleanFieldName);
}

From source file:com.meizu.nlp.classification.BooleanPerceptronClassifierTest.java

License:Apache License

@Test
public void testExplicitThreshold() throws Exception {
    checkCorrectClassification(new BooleanPerceptronClassifier(100d, 1), TECHNOLOGY_INPUT, false,
            new MockAnalyzer(random()), textFieldName, booleanFieldName);
}

From source file:com.meizu.nlp.classification.BooleanPerceptronClassifierTest.java

License:Apache License

@Test
public void testBasicUsageWithQuery() throws Exception {
    checkCorrectClassification(new BooleanPerceptronClassifier(), TECHNOLOGY_INPUT, false,
            new MockAnalyzer(random()), textFieldName, booleanFieldName,
            new TermQuery(new Term(textFieldName, "it")));
}

From source file:com.meizu.nlp.classification.BooleanPerceptronClassifierTest.java

License:Apache License

@Test
public void testPerformance() throws Exception {
    checkPerformance(new BooleanPerceptronClassifier(), new MockAnalyzer(random()), booleanFieldName);
}

From source file:com.meizu.nlp.classification.KNearestNeighborClassifierTest.java

License:Apache License

@Test
public void testBasicUsage() throws Exception {
    // usage with default MLT min docs / term freq
    checkCorrectClassification(new KNearestNeighborClassifier(3), POLITICS_INPUT, POLITICS_RESULT,
            new MockAnalyzer(random()), textFieldName, categoryFieldName);
    // usage without custom min docs / term freq for MLT
    checkCorrectClassification(new KNearestNeighborClassifier(3, 2, 1), TECHNOLOGY_INPUT, TECHNOLOGY_RESULT,
            new MockAnalyzer(random()), textFieldName, categoryFieldName);
}

From source file:com.meizu.nlp.classification.KNearestNeighborClassifierTest.java

License:Apache License

@Test
public void testBasicUsageWithQuery() throws Exception {
    checkCorrectClassification(new KNearestNeighborClassifier(1), TECHNOLOGY_INPUT, TECHNOLOGY_RESULT,
            new MockAnalyzer(random()), textFieldName, categoryFieldName,
            new TermQuery(new Term(textFieldName, "it")));
}

From source file:com.meizu.nlp.classification.KNearestNeighborClassifierTest.java

License:Apache License

@Test
public void testPerformance() throws Exception {
    checkPerformance(new KNearestNeighborClassifier(100), new MockAnalyzer(random()), categoryFieldName);
}

From source file:com.meizu.nlp.classification.SimpleNaiveBayesClassifierTest.java

License:Apache License

@Test
public void testBasicUsage() throws Exception {
    checkCorrectClassification(new SimpleNaiveBayesClassifier(), TECHNOLOGY_INPUT, TECHNOLOGY_RESULT,
            new MockAnalyzer(random()), textFieldName, categoryFieldName);
    checkCorrectClassification(new SimpleNaiveBayesClassifier(), POLITICS_INPUT, POLITICS_RESULT,
            new MockAnalyzer(random()), textFieldName, categoryFieldName);
}

From source file:com.meizu.nlp.classification.SimpleNaiveBayesClassifierTest.java

License:Apache License

@Test
public void testBasicUsageWithQuery() throws Exception {
    checkCorrectClassification(new SimpleNaiveBayesClassifier(), TECHNOLOGY_INPUT, TECHNOLOGY_RESULT,
            new MockAnalyzer(random()), textFieldName, categoryFieldName,
            new TermQuery(new Term(textFieldName, "it")));
}