Examples with IndexWriterConfig org.apache.lucene.index.IndexWriterConfig used on opensource projects

Example 91 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project lucene-solr by apache.

the class SimpleFacetsExample method index.

/** Build the example index. */
private void index() throws IOException {
    IndexWriter indexWriter = new IndexWriter(indexDir, new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE));
    // Writes facet ords to a separate directory from the main index
    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);
    Document doc = new Document();
    doc.add(new FacetField("Author", "Bob"));
    doc.add(new FacetField("Publish Date", "2010", "10", "15"));
    indexWriter.addDocument(config.build(taxoWriter, doc));
    doc = new Document();
    doc.add(new FacetField("Author", "Lisa"));
    doc.add(new FacetField("Publish Date", "2010", "10", "20"));
    indexWriter.addDocument(config.build(taxoWriter, doc));
    doc = new Document();
    doc.add(new FacetField("Author", "Lisa"));
    doc.add(new FacetField("Publish Date", "2012", "1", "1"));
    indexWriter.addDocument(config.build(taxoWriter, doc));
    doc = new Document();
    doc.add(new FacetField("Author", "Susan"));
    doc.add(new FacetField("Publish Date", "2012", "1", "7"));
    indexWriter.addDocument(config.build(taxoWriter, doc));
    doc = new Document();
    doc.add(new FacetField("Author", "Frank"));
    doc.add(new FacetField("Publish Date", "1999", "5", "5"));
    indexWriter.addDocument(config.build(taxoWriter, doc));
    indexWriter.close();
    taxoWriter.close();
}

Example 92 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project lucene-solr by apache.

the class TestExpressionValueSource method setUp.

@Override
public void setUp() throws Exception {
    super.setUp();
    dir = newDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig(new MockAnalyzer(random()));
    iwc.setMergePolicy(newLogMergePolicy());
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);
    Document doc = new Document();
    doc.add(newStringField("id", "1", Field.Store.YES));
    doc.add(newTextField("body", "some contents and more contents", Field.Store.NO));
    doc.add(new NumericDocValuesField("popularity", 5));
    iw.addDocument(doc);
    doc = new Document();
    doc.add(newStringField("id", "2", Field.Store.YES));
    doc.add(newTextField("body", "another document with different contents", Field.Store.NO));
    doc.add(new NumericDocValuesField("popularity", 20));
    doc.add(new NumericDocValuesField("count", 1));
    iw.addDocument(doc);
    doc = new Document();
    doc.add(newStringField("id", "3", Field.Store.YES));
    doc.add(newTextField("body", "crappy contents", Field.Store.NO));
    doc.add(new NumericDocValuesField("popularity", 2));
    iw.addDocument(doc);
    iw.forceMerge(1);
    reader = iw.getReader();
    iw.close();
}

Example 93 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project lucene-solr by apache.

the class TestQueryBitSetProducer method testSimple.

public void testSimple() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig().setMergePolicy(NoMergePolicy.INSTANCE);
    RandomIndexWriter w = new RandomIndexWriter(random(), dir, iwc);
    w.addDocument(new Document());
    DirectoryReader reader = w.getReader();
    QueryBitSetProducer producer = new QueryBitSetProducer(new MatchNoDocsQuery());
    assertNull(producer.getBitSet(reader.leaves().get(0)));
    assertEquals(1, producer.cache.size());
    producer = new QueryBitSetProducer(new MatchAllDocsQuery());
    BitSet bitSet = producer.getBitSet(reader.leaves().get(0));
    assertEquals(1, bitSet.length());
    assertEquals(true, bitSet.get(0));
    assertEquals(1, producer.cache.size());
    IOUtils.close(reader, w, dir);
}

Example 94 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project lucene-solr by apache.

the class IndexMergeTool method main.

public static void main(String[] args) throws IOException {
    if (args.length < 3) {
        System.err.println("Usage: IndexMergeTool <mergedIndex> <index1> <index2> [index3] ...");
        System.exit(1);
    }
    FSDirectory mergedIndex = FSDirectory.open(Paths.get(args[0]));
    IndexWriter writer = new IndexWriter(mergedIndex, new IndexWriterConfig(null).setOpenMode(OpenMode.CREATE));
    Directory[] indexes = new Directory[args.length - 1];
    for (int i = 1; i < args.length; i++) {
        // try to use hardlinks if possible
        indexes[i - 1] = new HardlinkCopyDirectoryWrapper(FSDirectory.open(Paths.get(args[i])));
    }
    System.out.println("Merging...");
    writer.addIndexes(indexes);
    System.out.println("Full merge...");
    writer.forceMerge(1);
    writer.close();
    System.out.println("Done.");
}

Example 95 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project lucene-solr by apache.

the class TestNearest method testNearestNeighborRandom.

public void testNearestNeighborRandom() throws Exception {
    int numPoints = atLeast(5000);
    Directory dir;
    if (numPoints > 100000) {
        dir = newFSDirectory(createTempDir(getClass().getSimpleName()));
    } else {
        dir = newDirectory();
    }
    double[] lats = new double[numPoints];
    double[] lons = new double[numPoints];
    IndexWriterConfig iwc = getIndexWriterConfig();
    iwc.setMergePolicy(newLogMergePolicy());
    iwc.setMergeScheduler(new SerialMergeScheduler());
    RandomIndexWriter w = new RandomIndexWriter(random(), dir, iwc);
    for (int id = 0; id < numPoints; id++) {
        lats[id] = quantizeLat(GeoTestUtil.nextLatitude());
        lons[id] = quantizeLon(GeoTestUtil.nextLongitude());
        Document doc = new Document();
        doc.add(new LatLonPoint("point", lats[id], lons[id]));
        doc.add(new LatLonDocValuesField("point", lats[id], lons[id]));
        doc.add(new StoredField("id", id));
        w.addDocument(doc);
    }
    if (random().nextBoolean()) {
        w.forceMerge(1);
    }
    DirectoryReader r = w.getReader();
    if (VERBOSE) {
        System.out.println("TEST: reader=" + r);
    }
    // can't wrap because we require Lucene60PointsFormat directly but e.g. ParallelReader wraps with its own points impl:
    IndexSearcher s = newSearcher(r, false);
    int iters = atLeast(100);
    for (int iter = 0; iter < iters; iter++) {
        if (VERBOSE) {
            System.out.println("\nTEST: iter=" + iter);
        }
        double pointLat = GeoTestUtil.nextLatitude();
        double pointLon = GeoTestUtil.nextLongitude();
        // dumb brute force search to get the expected result:
        NearestHit[] expectedHits = new NearestHit[lats.length];
        for (int id = 0; id < lats.length; id++) {
            NearestHit hit = new NearestHit();
            hit.distanceMeters = SloppyMath.haversinMeters(pointLat, pointLon, lats[id], lons[id]);
            hit.docID = id;
            expectedHits[id] = hit;
        }
        Arrays.sort(expectedHits, new Comparator<NearestHit>() {

            @Override
            public int compare(NearestHit a, NearestHit b) {
                int cmp = Double.compare(a.distanceMeters, b.distanceMeters);
                if (cmp != 0) {
                    return cmp;
                }
                // tie break by smaller docID:
                return a.docID - b.docID;
            }
        });
        int topN = TestUtil.nextInt(random(), 1, lats.length);
        if (VERBOSE) {
            System.out.println("\nhits for pointLat=" + pointLat + " pointLon=" + pointLon);
        }
        // Also test with MatchAllDocsQuery, sorting by distance:
        TopFieldDocs fieldDocs = s.search(new MatchAllDocsQuery(), topN, new Sort(LatLonDocValuesField.newDistanceSort("point", pointLat, pointLon)));
        ScoreDoc[] hits = LatLonPoint.nearest(s, "point", pointLat, pointLon, topN).scoreDocs;
        for (int i = 0; i < topN; i++) {
            NearestHit expected = expectedHits[i];
            FieldDoc expected2 = (FieldDoc) fieldDocs.scoreDocs[i];
            FieldDoc actual = (FieldDoc) hits[i];
            Document actualDoc = r.document(actual.doc);
            if (VERBOSE) {
                System.out.println("hit " + i);
                System.out.println("  expected id=" + expected.docID + " lat=" + lats[expected.docID] + " lon=" + lons[expected.docID] + " distance=" + expected.distanceMeters + " meters");
                System.out.println("  actual id=" + actualDoc.getField("id") + " distance=" + actual.fields[0] + " meters");
            }
            assertEquals(expected.docID, actual.doc);
            assertEquals(expected.distanceMeters, ((Double) actual.fields[0]).doubleValue(), 0.0);
            assertEquals(expected.docID, expected.docID);
            assertEquals(((Double) expected2.fields[0]).doubleValue(), expected.distanceMeters, 0.0);
        }
    }
    r.close();
    w.close();
    dir.close();
}