Examples with TextField org.apache.lucene.document.TextField used on opensource projects

Example 6 with TextField

use of org.apache.lucene.document.TextField in project elasticsearch by elastic.

the class LuceneTests method testCleanIndex.

public void testCleanIndex() throws IOException {
    MockDirectoryWrapper dir = newMockDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig();
    iwc.setIndexDeletionPolicy(NoDeletionPolicy.INSTANCE);
    iwc.setMergePolicy(NoMergePolicy.INSTANCE);
    iwc.setMaxBufferedDocs(2);
    IndexWriter writer = new IndexWriter(dir, iwc);
    Document doc = new Document();
    doc.add(new TextField("id", "1", random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
    writer.addDocument(doc);
    writer.commit();
    doc = new Document();
    doc.add(new TextField("id", "2", random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new TextField("id", "3", random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
    writer.addDocument(doc);
    writer.commit();
    doc = new Document();
    doc.add(new TextField("id", "4", random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
    writer.addDocument(doc);
    writer.deleteDocuments(new Term("id", "2"));
    writer.commit();
    try (DirectoryReader open = DirectoryReader.open(writer)) {
        assertEquals(3, open.numDocs());
        assertEquals(1, open.numDeletedDocs());
        assertEquals(4, open.maxDoc());
    }
    writer.close();
    if (random().nextBoolean()) {
        for (String file : dir.listAll()) {
            if (file.startsWith("_1")) {
                // delete a random file
                dir.deleteFile(file);
                break;
            }
        }
    }
    Lucene.cleanLuceneIndex(dir);
    if (dir.listAll().length > 0) {
        for (String file : dir.listAll()) {
            if (file.startsWith("extra") == false) {
                assertEquals(file, "write.lock");
            }
        }
    }
    dir.close();
}

Example 7 with TextField

use of org.apache.lucene.document.TextField in project elasticsearch by elastic.

the class LuceneTests method testNumDocs.

public void testNumDocs() throws IOException {
    MockDirectoryWrapper dir = newMockDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig();
    IndexWriter writer = new IndexWriter(dir, iwc);
    Document doc = new Document();
    doc.add(new TextField("id", "1", random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
    writer.addDocument(doc);
    writer.commit();
    SegmentInfos segmentCommitInfos = Lucene.readSegmentInfos(dir);
    assertEquals(1, Lucene.getNumDocs(segmentCommitInfos));
    doc = new Document();
    doc.add(new TextField("id", "2", random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new TextField("id", "3", random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
    writer.addDocument(doc);
    segmentCommitInfos = Lucene.readSegmentInfos(dir);
    assertEquals(1, Lucene.getNumDocs(segmentCommitInfos));
    writer.commit();
    segmentCommitInfos = Lucene.readSegmentInfos(dir);
    assertEquals(3, Lucene.getNumDocs(segmentCommitInfos));
    writer.deleteDocuments(new Term("id", "2"));
    writer.commit();
    segmentCommitInfos = Lucene.readSegmentInfos(dir);
    assertEquals(2, Lucene.getNumDocs(segmentCommitInfos));
    int numDocsToIndex = randomIntBetween(10, 50);
    List<Term> deleteTerms = new ArrayList<>();
    for (int i = 0; i < numDocsToIndex; i++) {
        doc = new Document();
        doc.add(new TextField("id", "extra_" + i, random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
        deleteTerms.add(new Term("id", "extra_" + i));
        writer.addDocument(doc);
    }
    int numDocsToDelete = randomIntBetween(0, numDocsToIndex);
    Collections.shuffle(deleteTerms, random());
    for (int i = 0; i < numDocsToDelete; i++) {
        Term remove = deleteTerms.remove(0);
        writer.deleteDocuments(remove);
    }
    writer.commit();
    segmentCommitInfos = Lucene.readSegmentInfos(dir);
    assertEquals(2 + deleteTerms.size(), Lucene.getNumDocs(segmentCommitInfos));
    writer.close();
    dir.close();
}

Example 8 with TextField

use of org.apache.lucene.document.TextField in project elasticsearch by elastic.

the class LuceneTests method testWaitForIndex.

public void testWaitForIndex() throws Exception {
    final MockDirectoryWrapper dir = newMockDirectory();
    final AtomicBoolean succeeded = new AtomicBoolean(false);
    final CountDownLatch latch = new CountDownLatch(1);
    // Create a shadow Engine, which will freak out because there is no
    // index yet
    Thread t = new Thread(new Runnable() {

        @Override
        public void run() {
            try {
                latch.await();
                if (Lucene.waitForIndex(dir, 5000)) {
                    succeeded.set(true);
                } else {
                    fail("index should have eventually existed!");
                }
            } catch (InterruptedException e) {
            // ignore interruptions
            } catch (Exception e) {
                fail("should have been able to create the engine! " + e.getMessage());
            }
        }
    });
    t.start();
    // count down latch
    // now shadow engine should try to be created
    latch.countDown();
    IndexWriterConfig iwc = newIndexWriterConfig();
    iwc.setIndexDeletionPolicy(NoDeletionPolicy.INSTANCE);
    iwc.setMergePolicy(NoMergePolicy.INSTANCE);
    iwc.setMaxBufferedDocs(2);
    IndexWriter writer = new IndexWriter(dir, iwc);
    Document doc = new Document();
    doc.add(new TextField("id", "1", random().nextBoolean() ? Field.Store.YES : Field.Store.NO));
    writer.addDocument(doc);
    writer.commit();
    t.join();
    writer.close();
    dir.close();
    assertTrue("index should have eventually existed", succeeded.get());
}

Example 9 with TextField

use of org.apache.lucene.document.TextField in project elasticsearch by elastic.

the class SimpleLuceneTests method testNRTSearchOnClosedWriter.

public void testNRTSearchOnClosedWriter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    DirectoryReader reader = DirectoryReader.open(indexWriter);
    for (int i = 0; i < 100; i++) {
        Document document = new Document();
        TextField field = new TextField("_id", Integer.toString(i), Field.Store.YES);
        field.setBoost(i);
        document.add(field);
        indexWriter.addDocument(document);
    }
    reader = refreshReader(reader);
    indexWriter.close();
    TermsEnum termDocs = SlowCompositeReaderWrapper.wrap(reader).terms("_id").iterator();
    termDocs.next();
}

Example 10 with TextField

use of org.apache.lucene.document.TextField 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();
}