Examples with PhraseQuery org.apache.lucene.search.PhraseQuery used on opensource projects

Example 26 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class TestBooleanSimilarity method testPhraseScoreIsEqualToBoost.

public void testPhraseScoreIsEqualToBoost() throws IOException {
    Directory dir = newDirectory();
    RandomIndexWriter w = new RandomIndexWriter(random(), dir, newIndexWriterConfig().setSimilarity(new BooleanSimilarity()));
    Document doc = new Document();
    doc.add(new TextField("foo", "bar baz quux", Store.NO));
    w.addDocument(doc);
    DirectoryReader reader = w.getReader();
    w.close();
    IndexSearcher searcher = newSearcher(reader);
    searcher.setSimilarity(new BooleanSimilarity());
    PhraseQuery query = new PhraseQuery(2, "foo", "bar", "quux");
    TopDocs topDocs = searcher.search(query, 2);
    assertEquals(1, topDocs.totalHits);
    assertEquals(1f, topDocs.scoreDocs[0].score, 0f);
    topDocs = searcher.search(new BoostQuery(query, 7), 2);
    assertEquals(1, topDocs.totalHits);
    assertEquals(7f, topDocs.scoreDocs[0].score, 0f);
    reader.close();
    dir.close();
}

Example 27 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class FastVectorHighlighterTest method clause.

private Query clause(String field, float boost, String... terms) {
    Query q;
    if (terms.length == 1) {
        q = new TermQuery(new Term(field, terms[0]));
    } else {
        q = new PhraseQuery(field, terms);
    }
    q = new BoostQuery(q, boost);
    return q;
}

Example 28 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class FastVectorHighlighterTest method testBooleanPhraseWithSynonym.

public void testBooleanPhraseWithSynonym() throws IOException {
    Directory dir = newDirectory();
    IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(new MockAnalyzer(random())));
    Document doc = new Document();
    FieldType type = new FieldType(TextField.TYPE_NOT_STORED);
    type.setStoreTermVectorOffsets(true);
    type.setStoreTermVectorPositions(true);
    type.setStoreTermVectors(true);
    type.freeze();
    Token syn = new Token("httpwwwfacebookcom", 6, 29);
    syn.setPositionIncrement(0);
    CannedTokenStream ts = new CannedTokenStream(new Token("test", 0, 4), new Token("http", 6, 10), syn, new Token("www", 13, 16), new Token("facebook", 17, 25), new Token("com", 26, 29));
    Field field = new Field("field", ts, type);
    doc.add(field);
    doc.add(new StoredField("field", "Test: http://www.facebook.com"));
    writer.addDocument(doc);
    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    IndexReader reader = DirectoryReader.open(writer);
    int docId = 0;
    // query1: match
    PhraseQuery pq = new PhraseQuery("field", "test", "http", "www", "facebook", "com");
    FieldQuery fieldQuery = highlighter.getFieldQuery(pq, reader);
    String[] bestFragments = highlighter.getBestFragments(fieldQuery, reader, docId, "field", 54, 1);
    assertEquals("<b>Test: http://www.facebook.com</b>", bestFragments[0]);
    // query2: match
    PhraseQuery pq2 = new PhraseQuery("field", "test", "httpwwwfacebookcom", "www", "facebook", "com");
    fieldQuery = highlighter.getFieldQuery(pq2, reader);
    bestFragments = highlighter.getBestFragments(fieldQuery, reader, docId, "field", 54, 1);
    assertEquals("<b>Test: http://www.facebook.com</b>", bestFragments[0]);
    // query3: OR query1 and query2 together
    BooleanQuery.Builder bq = new BooleanQuery.Builder();
    bq.add(pq, BooleanClause.Occur.SHOULD);
    bq.add(pq2, BooleanClause.Occur.SHOULD);
    fieldQuery = highlighter.getFieldQuery(bq.build(), reader);
    bestFragments = highlighter.getBestFragments(fieldQuery, reader, docId, "field", 54, 1);
    assertEquals("<b>Test: http://www.facebook.com</b>", bestFragments[0]);
    reader.close();
    writer.close();
    dir.close();
}

Example 29 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class FastVectorHighlighterTest method testPhraseHighlightLongTextTest.

public void testPhraseHighlightLongTextTest() throws IOException {
    Directory dir = newDirectory();
    IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(new MockAnalyzer(random())));
    Document doc = new Document();
    FieldType type = new FieldType(TextField.TYPE_STORED);
    type.setStoreTermVectorOffsets(true);
    type.setStoreTermVectorPositions(true);
    type.setStoreTermVectors(true);
    type.freeze();
    Field text = new Field("text", "Netscape was the general name for a series of web browsers originally produced by Netscape Communications Corporation, now a subsidiary of AOL The original browser was once the dominant browser in terms of usage share, but as a result of the first browser war it lost virtually all of its share to Internet Explorer Netscape was discontinued and support for all Netscape browsers and client products was terminated on March 1, 2008 Netscape Navigator was the name of Netscape's web browser from versions 1.0 through 4.8 The first beta release versions of the browser were released in 1994 and known as Mosaic and then Mosaic Netscape until a legal challenge from the National Center for Supercomputing Applications (makers of NCSA Mosaic, which many of Netscape's founders used to develop), led to the name change to Netscape Navigator The company's name also changed from Mosaic Communications Corporation to Netscape Communications Corporation The browser was easily the most advanced...", type);
    doc.add(text);
    writer.addDocument(doc);
    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    IndexReader reader = DirectoryReader.open(writer);
    int docId = 0;
    String field = "text";
    {
        BooleanQuery.Builder query = new BooleanQuery.Builder();
        query.add(new TermQuery(new Term(field, "internet")), Occur.MUST);
        query.add(new TermQuery(new Term(field, "explorer")), Occur.MUST);
        FieldQuery fieldQuery = highlighter.getFieldQuery(query.build(), reader);
        String[] bestFragments = highlighter.getBestFragments(fieldQuery, reader, docId, field, 128, 1);
        // highlighted results are centered
        assertEquals(1, bestFragments.length);
        assertEquals("first browser war it lost virtually all of its share to <b>Internet</b> <b>Explorer</b> Netscape was discontinued and support for all Netscape browsers", bestFragments[0]);
    }
    {
        PhraseQuery query = new PhraseQuery(field, "internet", "explorer");
        FieldQuery fieldQuery = highlighter.getFieldQuery(query, reader);
        String[] bestFragments = highlighter.getBestFragments(fieldQuery, reader, docId, field, 128, 1);
        // highlighted results are centered
        assertEquals(1, bestFragments.length);
        assertEquals("first browser war it lost virtually all of its share to <b>Internet Explorer</b> Netscape was discontinued and support for all Netscape browsers", bestFragments[0]);
    }
    reader.close();
    writer.close();
    dir.close();
}

Example 30 with PhraseQuery

use of org.apache.lucene.search.PhraseQuery in project lucene-solr by apache.

the class TestUnifiedHighlighterMTQ method testPositionSensitiveWithWildcardDoesNotHighlight.

public void testPositionSensitiveWithWildcardDoesNotHighlight() throws Exception {
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, indexAnalyzer);
    Document doc = new Document();
    doc.add(new Field("body", "iterate insect ipswitch illinois indirect", fieldType));
    doc.add(newTextField("id", "id", Field.Store.YES));
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher searcher = newSearcher(ir);
    UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
    int docID = searcher.search(new TermQuery(new Term("id", "id")), 1).scoreDocs[0].doc;
    PhraseQuery pq = new PhraseQuery.Builder().add(new Term("body", "consent")).add(new Term("body", "order")).build();
    BooleanQuery query = new BooleanQuery.Builder().add(new WildcardQuery(new Term("body", "enforc*")), BooleanClause.Occur.MUST).add(pq, BooleanClause.Occur.MUST).build();
    int[] docIds = new int[] { docID };
    String[] snippets = highlighter.highlightFields(new String[] { "body" }, query, docIds, new int[] { 2 }).get("body");
    assertEquals(1, snippets.length);
    assertEquals("iterate insect ipswitch illinois indirect", snippets[0]);
    ir.close();
}