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

Example 81 with TopDocs

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

the class TestUnifiedHighlighter method testCuriousGeorge.

public void testCuriousGeorge() throws Exception {
    String text = "It’s the formula for success for preschoolers—Curious George and fire trucks! " + "Curious George and the Firefighters is a story based on H. A. and Margret Rey’s " + "popular primate and painted in the original watercolor and charcoal style. " + "Firefighters are a famously brave lot, but can they withstand a visit from one curious monkey?";
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, indexAnalyzer);
    Field body = new Field("body", text, fieldType);
    Document document = new Document();
    document.add(body);
    iw.addDocument(document);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher searcher = newSearcher(ir);
    PhraseQuery query = new PhraseQuery.Builder().add(new Term("body", "curious")).add(new Term("body", "george")).build();
    TopDocs topDocs = searcher.search(query, 10);
    assertEquals(1, topDocs.totalHits);
    UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
    highlighter.setHighlightPhrasesStrictly(false);
    String[] snippets = highlighter.highlight("body", query, topDocs, 2);
    assertEquals(1, snippets.length);
    assertFalse(snippets[0].contains("<b>Curious</b>Curious"));
    ir.close();
}

Example 82 with TopDocs

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

the class SynonymTokenizer method testQueryScorerHits.

public void testQueryScorerHits() throws Exception {
    PhraseQuery phraseQuery = new PhraseQuery(FIELD_NAME, "very", "long");
    query = phraseQuery;
    searcher = newSearcher(reader);
    TopDocs hits = searcher.search(query, 10);
    QueryScorer scorer = new QueryScorer(query, FIELD_NAME);
    Highlighter highlighter = new Highlighter(scorer);
    for (int i = 0; i < hits.scoreDocs.length; i++) {
        final int docId = hits.scoreDocs[i].doc;
        Document doc = searcher.doc(docId);
        String storedField = doc.get(FIELD_NAME);
        TokenStream stream = getAnyTokenStream(FIELD_NAME, docId);
        Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
        highlighter.setTextFragmenter(fragmenter);
        String fragment = highlighter.getBestFragment(stream, storedField);
        if (VERBOSE)
            System.out.println(fragment);
    }
}

Example 83 with TopDocs

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

the class SimplePrimaryNode method verifyAtLeastMarkerCount.

private void verifyAtLeastMarkerCount(int expectedAtLeastCount, DataOutput out) throws IOException {
    IndexSearcher searcher = mgr.acquire();
    try {
        long version = ((DirectoryReader) searcher.getIndexReader()).getVersion();
        int hitCount = searcher.count(new TermQuery(new Term("marker", "marker")));
        if (hitCount < expectedAtLeastCount) {
            message("marker search: expectedAtLeastCount=" + expectedAtLeastCount + " but hitCount=" + hitCount);
            TopDocs hits = searcher.search(new TermQuery(new Term("marker", "marker")), expectedAtLeastCount);
            List<Integer> seen = new ArrayList<>();
            for (ScoreDoc hit : hits.scoreDocs) {
                Document doc = searcher.doc(hit.doc);
                seen.add(Integer.parseInt(doc.get("docid").substring(1)));
            }
            Collections.sort(seen);
            message("saw markers:");
            for (int marker : seen) {
                message("saw m" + marker);
            }
            throw new IllegalStateException("at flush: marker count " + hitCount + " but expected at least " + expectedAtLeastCount + " version=" + version);
        }
        if (out != null) {
            out.writeVLong(version);
            out.writeVInt(hitCount);
        }
    } finally {
        mgr.release(searcher);
    }
}

Example 84 with TopDocs

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

the class BaseGeoPointTestCase method searchSmallSet.

/** return topdocs over a small set of points in field "point" */
private TopDocs searchSmallSet(Query query, int size) throws Exception {
    // this is a simple systematic test, indexing these points
    // TODO: fragile: does not understand quantization in any way yet uses extremely high precision!
    double[][] pts = new double[][] { { 32.763420, -96.774 }, { 32.7559529921407, -96.7759895324707 }, { 32.77866942010977, -96.77701950073242 }, { 32.7756745755423, -96.7706036567688 }, { 27.703618681345585, -139.73458170890808 }, { 32.94823588839368, -96.4538113027811 }, { 33.06047141970814, -96.65084838867188 }, { 32.778650, -96.7772 }, { -88.56029371730983, -177.23537676036358 }, { 33.541429799076354, -26.779373834241003 }, { 26.774024500421728, -77.35379276106497 }, { -90.0, -14.796283808944777 }, { 32.94823588839368, -178.8538113027811 }, { 32.94823588839368, 178.8538113027811 }, { 40.720611, -73.998776 }, { -44.5, -179.5 } };
    Directory directory = newDirectory();
    // TODO: must these simple tests really rely on docid order?
    IndexWriterConfig iwc = newIndexWriterConfig(new MockAnalyzer(random()));
    iwc.setMaxBufferedDocs(TestUtil.nextInt(random(), 100, 1000));
    iwc.setMergePolicy(newLogMergePolicy());
    // Else seeds may not reproduce:
    iwc.setMergeScheduler(new SerialMergeScheduler());
    RandomIndexWriter writer = new RandomIndexWriter(random(), directory, iwc);
    for (double[] p : pts) {
        Document doc = new Document();
        addPointToDoc("point", doc, p[0], p[1]);
        writer.addDocument(doc);
    }
    // add explicit multi-valued docs
    for (int i = 0; i < pts.length; i += 2) {
        Document doc = new Document();
        addPointToDoc("point", doc, pts[i][0], pts[i][1]);
        addPointToDoc("point", doc, pts[i + 1][0], pts[i + 1][1]);
        writer.addDocument(doc);
    }
    // index random string documents
    for (int i = 0; i < random().nextInt(10); ++i) {
        Document doc = new Document();
        doc.add(new StringField("string", Integer.toString(i), Field.Store.NO));
        writer.addDocument(doc);
    }
    IndexReader reader = writer.getReader();
    writer.close();
    IndexSearcher searcher = newSearcher(reader);
    TopDocs topDocs = searcher.search(query, size);
    reader.close();
    directory.close();
    return topDocs;
}

Example 85 with TopDocs

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

the class BaseGeoPointTestCase method testSmallSetRect.

public void testSmallSetRect() throws Exception {
    TopDocs td = searchSmallSet(newRectQuery("point", 32.778, 32.779, -96.778, -96.777), 5);
    assertEquals(4, td.totalHits);
}