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

Example 21 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project elasticsearch by elastic.

the class SimpleLuceneTests method testBoost.

public void testBoost() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    for (int i = 0; i < 100; i++) {
        // TODO (just setting the boost value does not seem to work...)
        StringBuilder value = new StringBuilder().append("value");
        for (int j = 0; j < i; j++) {
            value.append(" ").append("value");
        }
        Document document = new Document();
        TextField textField = new TextField("_id", Integer.toString(i), Field.Store.YES);
        textField.setBoost(i);
        document.add(textField);
        textField = new TextField("value", value.toString(), Field.Store.YES);
        textField.setBoost(i);
        document.add(textField);
        indexWriter.addDocument(document);
    }
    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TermQuery query = new TermQuery(new Term("value", "value"));
    TopDocs topDocs = searcher.search(query, 100);
    assertThat(100, equalTo(topDocs.totalHits));
    for (int i = 0; i < topDocs.scoreDocs.length; i++) {
        Document doc = searcher.doc(topDocs.scoreDocs[i].doc);
        //            System.out.println(doc.get("id") + ": " + searcher.explain(query, topDocs.scoreDocs[i].doc));
        assertThat(doc.get("_id"), equalTo(Integer.toString(100 - i - 1)));
    }
    indexWriter.close();
}

Example 22 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project elasticsearch by elastic.

the class SimpleLuceneTests method testOrdering.

/**
     * Here, we verify that the order that we add fields to a document counts, and not the lexi order
     * of the field. This means that heavily accessed fields that use field selector should be added
     * first (with load and break).
     */
public void testOrdering() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new TextField("#id", "1", Field.Store.YES));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
    final ArrayList<String> fieldsOrder = new ArrayList<>();
    searcher.doc(topDocs.scoreDocs[0].doc, new StoredFieldVisitor() {

        @Override
        public Status needsField(FieldInfo fieldInfo) throws IOException {
            fieldsOrder.add(fieldInfo.name);
            return Status.YES;
        }
    });
    assertThat(fieldsOrder.size(), equalTo(2));
    assertThat(fieldsOrder.get(0), equalTo("_id"));
    assertThat(fieldsOrder.get(1), equalTo("#id"));
    indexWriter.close();
}

Example 23 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project elasticsearch by elastic.

the class VectorHighlighterTests method testVectorHighlighterNoTermVector.

public void testVectorHighlighterNoTermVector() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new TextField("content", "the big bad dog", Field.Store.YES));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
    assertThat(topDocs.totalHits, equalTo(1));
    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader, topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, nullValue());
}

Example 24 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project elasticsearch by elastic.

the class VectorHighlighterTests method testVectorHighlighter.

public void testVectorHighlighter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    FieldType vectorsType = new FieldType(TextField.TYPE_STORED);
    vectorsType.setStoreTermVectors(true);
    vectorsType.setStoreTermVectorPositions(true);
    vectorsType.setStoreTermVectorOffsets(true);
    document.add(new Field("content", "the big bad dog", vectorsType));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);
    assertThat(topDocs.totalHits, equalTo(1));
    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader, topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());
    assertThat(fragment, equalTo("the big <b>bad</b> dog"));
}

Example 25 with IndexWriterConfig

use of org.apache.lucene.index.IndexWriterConfig in project elasticsearch by elastic.

the class FieldDataCacheTests method testLoadGlobal_neverCacheIfFieldIsMissing.

public void testLoadGlobal_neverCacheIfFieldIsMissing() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = new IndexWriterConfig(null);
    iwc.setMergePolicy(NoMergePolicy.INSTANCE);
    IndexWriter iw = new IndexWriter(dir, iwc);
    long numDocs = scaledRandomIntBetween(32, 128);
    for (int i = 1; i <= numDocs; i++) {
        Document doc = new Document();
        doc.add(new SortedSetDocValuesField("field1", new BytesRef(String.valueOf(i))));
        doc.add(new StringField("field2", String.valueOf(i), Field.Store.NO));
        iw.addDocument(doc);
        if (i % 24 == 0) {
            iw.commit();
        }
    }
    iw.close();
    DirectoryReader ir = ElasticsearchDirectoryReader.wrap(DirectoryReader.open(dir), new ShardId("_index", "_na_", 0));
    DummyAccountingFieldDataCache fieldDataCache = new DummyAccountingFieldDataCache();
    // Testing SortedSetDVOrdinalsIndexFieldData:
    SortedSetDVOrdinalsIndexFieldData sortedSetDVOrdinalsIndexFieldData = createSortedDV("field1", fieldDataCache);
    sortedSetDVOrdinalsIndexFieldData.loadGlobal(ir);
    assertThat(fieldDataCache.cachedGlobally, equalTo(1));
    sortedSetDVOrdinalsIndexFieldData.loadGlobal(new FieldMaskingReader("field1", ir));
    assertThat(fieldDataCache.cachedGlobally, equalTo(1));
    // Testing PagedBytesIndexFieldData
    PagedBytesIndexFieldData pagedBytesIndexFieldData = createPagedBytes("field2", fieldDataCache);
    pagedBytesIndexFieldData.loadGlobal(ir);
    assertThat(fieldDataCache.cachedGlobally, equalTo(2));
    pagedBytesIndexFieldData.loadGlobal(new FieldMaskingReader("field2", ir));
    assertThat(fieldDataCache.cachedGlobally, equalTo(2));
    ir.close();
    dir.close();
}