Examples with SpanTermQuery org.apache.lucene.search.spans.SpanTermQuery used on opensource projects

Example 51 with SpanTermQuery

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

the class TestSimilarity2 method testCrazySpans.

/** make sure all sims work with spanOR(termX, termY) where termY does not exist */
public void testCrazySpans() throws Exception {
    // The problem: "normal" lucene queries create scorers, returning null if terms dont exist
    // This means they never score a term that does not exist.
    // however with spans, there is only one scorer for the whole hierarchy:
    // inner queries are not real queries, their boosts are ignored, etc.
    Directory dir = newDirectory();
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir);
    Document doc = new Document();
    FieldType ft = new FieldType(TextField.TYPE_NOT_STORED);
    doc.add(newField("foo", "bar", ft));
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher is = newSearcher(ir);
    for (Similarity sim : sims) {
        is.setSimilarity(sim);
        SpanTermQuery s1 = new SpanTermQuery(new Term("foo", "bar"));
        SpanTermQuery s2 = new SpanTermQuery(new Term("foo", "baz"));
        Query query = new SpanOrQuery(s1, s2);
        TopDocs td = is.search(query, 10);
        assertEquals(1, td.totalHits);
        float score = td.scoreDocs[0].score;
        assertFalse("negative score for " + sim, score < 0.0f);
        assertFalse("inf score for " + sim, Float.isInfinite(score));
        assertFalse("nan score for " + sim, Float.isNaN(score));
    }
    ir.close();
    dir.close();
}

Example 52 with SpanTermQuery

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

the class TestPayloadTermQuery method testNoPayload.

public void testNoPayload() throws Exception {
    SpanQuery q1 = new PayloadScoreQuery(new SpanTermQuery(new Term(PayloadHelper.NO_PAYLOAD_FIELD, "zero")), new MaxPayloadFunction());
    SpanQuery q2 = new PayloadScoreQuery(new SpanTermQuery(new Term(PayloadHelper.NO_PAYLOAD_FIELD, "foo")), new MaxPayloadFunction());
    BooleanClause c1 = new BooleanClause(q1, BooleanClause.Occur.MUST);
    BooleanClause c2 = new BooleanClause(q2, BooleanClause.Occur.MUST_NOT);
    BooleanQuery.Builder query = new BooleanQuery.Builder();
    query.add(c1);
    query.add(c2);
    TopDocs hits = searcher.search(query.build(), 100);
    assertTrue("hits is null and it shouldn't be", hits != null);
    assertTrue("hits Size: " + hits.totalHits + " is not: " + 1, hits.totalHits == 1);
    int[] results = new int[1];
    //hits.scoreDocs[0].doc;
    results[0] = 0;
    CheckHits.checkHitCollector(random(), query.build(), PayloadHelper.NO_PAYLOAD_FIELD, searcher, results);
}

Example 53 with SpanTermQuery

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

the class TestPayloadTermQuery method testQuery.

public void testQuery() {
    SpanQuery boostingFuncTermQuery = new PayloadScoreQuery(new SpanTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy")), new MaxPayloadFunction());
    QueryUtils.check(boostingFuncTermQuery);
    SpanTermQuery spanTermQuery = new SpanTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy"));
    assertTrue(boostingFuncTermQuery.equals(spanTermQuery) == spanTermQuery.equals(boostingFuncTermQuery));
    SpanQuery boostingFuncTermQuery2 = new PayloadScoreQuery(new SpanTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy")), new AveragePayloadFunction());
    QueryUtils.checkUnequal(boostingFuncTermQuery, boostingFuncTermQuery2);
}

Example 54 with SpanTermQuery

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

the class TestPayloadScoreQuery method testNestedNearQuery.

@Test
public void testNestedNearQuery() throws Exception {
    // (one OR hundred) NEAR (twenty two) ~ 1
    //  2    4        4    4
    // one hundred twenty two
    // two hundred twenty two
    SpanNearQuery q = new SpanNearQuery(new SpanQuery[] { new SpanOrQuery(new SpanTermQuery(new Term("field", "one")), new SpanTermQuery(new Term("field", "hundred"))), new SpanNearQuery(new SpanQuery[] { new SpanTermQuery(new Term("field", "twenty")), new SpanTermQuery(new Term("field", "two")) }, 0, true) }, 1, true);
    // check includeSpanScore makes a difference here
    searcher.setSimilarity(new MultiplyingSimilarity());
    try {
        checkQuery(q, new MaxPayloadFunction(), new int[] { 122, 222 }, new float[] { 20.901256561279297f, 17.06580352783203f });
        checkQuery(q, new MinPayloadFunction(), new int[] { 222, 122 }, new float[] { 17.06580352783203f, 10.450628280639648f });
        checkQuery(q, new AveragePayloadFunction(), new int[] { 122, 222 }, new float[] { 19.15948486328125f, 17.06580352783203f });
        checkQuery(q, new MaxPayloadFunction(), false, new int[] { 122, 222 }, new float[] { 4.0f, 4.0f });
        checkQuery(q, new MinPayloadFunction(), false, new int[] { 222, 122 }, new float[] { 4.0f, 2.0f });
        checkQuery(q, new AveragePayloadFunction(), false, new int[] { 222, 122 }, new float[] { 4.0f, 3.666666f });
    } finally {
        searcher.setSimilarity(similarity);
    }
}

Example 55 with SpanTermQuery

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

the class TestPayloadSpans method testShrinkToAfterShortestMatch.

public void testShrinkToAfterShortestMatch() throws IOException {
    Directory directory = newDirectory();
    RandomIndexWriter writer = new RandomIndexWriter(random(), directory, newIndexWriterConfig(new TestPayloadAnalyzer()));
    Document doc = new Document();
    doc.add(new TextField("content", new StringReader("a b c d e f g h i j a k")));
    writer.addDocument(doc);
    IndexReader reader = writer.getReader();
    IndexSearcher is = newSearcher(getOnlyLeafReader(reader), false);
    writer.close();
    SpanTermQuery stq1 = new SpanTermQuery(new Term("content", "a"));
    SpanTermQuery stq2 = new SpanTermQuery(new Term("content", "k"));
    SpanQuery[] sqs = { stq1, stq2 };
    SpanNearQuery snq = new SpanNearQuery(sqs, 1, true);
    VerifyingCollector collector = new VerifyingCollector();
    Spans spans = snq.createWeight(is, false, 1f).getSpans(is.getIndexReader().leaves().get(0), SpanWeight.Postings.PAYLOADS);
    TopDocs topDocs = is.search(snq, 1);
    Set<String> payloadSet = new HashSet<>();
    for (int i = 0; i < topDocs.scoreDocs.length; i++) {
        while (spans.nextDoc() != Spans.NO_MORE_DOCS) {
            while (spans.nextStartPosition() != Spans.NO_MORE_POSITIONS) {
                collector.reset();
                spans.collect(collector);
                for (final BytesRef payload : collector.payloads) {
                    payloadSet.add(Term.toString(payload));
                }
            }
        }
    }
    assertEquals(2, payloadSet.size());
    assertTrue(payloadSet.contains("a:Noise:10"));
    assertTrue(payloadSet.contains("k:Noise:11"));
    reader.close();
    directory.close();
}