Search in sources :

Example 56 with LeafReader

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

the class TestFieldCache method testEmptyIndex.

public void testEmptyIndex() throws Exception {
    Directory dir = newDirectory();
    IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(new MockAnalyzer(random())).setMaxBufferedDocs(500));
    writer.close();
    IndexReader r = DirectoryReader.open(dir);
    LeafReader reader = SlowCompositeReaderWrapper.wrap(r);
    TestUtil.checkReader(reader);
    FieldCache.DEFAULT.getTerms(reader, "foobar");
    FieldCache.DEFAULT.getTermsIndex(reader, "foobar");
    FieldCache.DEFAULT.purgeByCacheKey(reader.getCoreCacheHelper().getKey());
    r.close();
    dir.close();
}
Also used : MockAnalyzer(org.apache.lucene.analysis.MockAnalyzer) LeafReader(org.apache.lucene.index.LeafReader) IndexWriter(org.apache.lucene.index.IndexWriter) RandomIndexWriter(org.apache.lucene.index.RandomIndexWriter) IndexReader(org.apache.lucene.index.IndexReader) Directory(org.apache.lucene.store.Directory)

Example 57 with LeafReader

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

the class TestFieldCache method testDocValuesIntegration.

public void testDocValuesIntegration() throws Exception {
    Directory dir = newDirectory();
    IndexWriterConfig iwc = newIndexWriterConfig(null);
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, iwc);
    Document doc = new Document();
    doc.add(new BinaryDocValuesField("binary", new BytesRef("binary value")));
    doc.add(new SortedDocValuesField("sorted", new BytesRef("sorted value")));
    doc.add(new NumericDocValuesField("numeric", 42));
    doc.add(new SortedSetDocValuesField("sortedset", new BytesRef("sortedset value1")));
    doc.add(new SortedSetDocValuesField("sortedset", new BytesRef("sortedset value2")));
    iw.addDocument(doc);
    DirectoryReader ir = iw.getReader();
    iw.close();
    LeafReader ar = getOnlyLeafReader(ir);
    // Binary type: can be retrieved via getTerms()
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getNumerics(ar, "binary", FieldCache.INT_POINT_PARSER);
    });
    BinaryDocValues binary = FieldCache.DEFAULT.getTerms(ar, "binary");
    assertEquals(0, binary.nextDoc());
    final BytesRef term = binary.binaryValue();
    assertEquals("binary value", term.utf8ToString());
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTermsIndex(ar, "binary");
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getDocTermOrds(ar, "binary", null);
    });
    expectThrows(IllegalStateException.class, () -> {
        new DocTermOrds(ar, null, "binary");
    });
    Bits bits = FieldCache.DEFAULT.getDocsWithField(ar, "binary", null);
    assertTrue(bits.get(0));
    // Sorted type: can be retrieved via getTerms(), getTermsIndex(), getDocTermOrds()
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getNumerics(ar, "sorted", FieldCache.INT_POINT_PARSER);
    });
    expectThrows(IllegalStateException.class, () -> {
        new DocTermOrds(ar, null, "sorted");
    });
    binary = FieldCache.DEFAULT.getTerms(ar, "sorted");
    assertEquals(0, binary.nextDoc());
    BytesRef scratch = binary.binaryValue();
    assertEquals("sorted value", scratch.utf8ToString());
    SortedDocValues sorted = FieldCache.DEFAULT.getTermsIndex(ar, "sorted");
    assertEquals(0, sorted.nextDoc());
    assertEquals(0, sorted.ordValue());
    assertEquals(1, sorted.getValueCount());
    scratch = sorted.binaryValue();
    assertEquals("sorted value", scratch.utf8ToString());
    SortedSetDocValues sortedSet = FieldCache.DEFAULT.getDocTermOrds(ar, "sorted", null);
    assertEquals(0, sortedSet.nextDoc());
    assertEquals(0, sortedSet.nextOrd());
    assertEquals(SortedSetDocValues.NO_MORE_ORDS, sortedSet.nextOrd());
    assertEquals(1, sortedSet.getValueCount());
    bits = FieldCache.DEFAULT.getDocsWithField(ar, "sorted", null);
    assertTrue(bits.get(0));
    // Numeric type: can be retrieved via getInts() and so on
    NumericDocValues numeric = FieldCache.DEFAULT.getNumerics(ar, "numeric", FieldCache.INT_POINT_PARSER);
    assertEquals(0, numeric.nextDoc());
    assertEquals(42, numeric.longValue());
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTerms(ar, "numeric");
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTermsIndex(ar, "numeric");
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getDocTermOrds(ar, "numeric", null);
    });
    expectThrows(IllegalStateException.class, () -> {
        new DocTermOrds(ar, null, "numeric");
    });
    bits = FieldCache.DEFAULT.getDocsWithField(ar, "numeric", null);
    assertTrue(bits.get(0));
    // SortedSet type: can be retrieved via getDocTermOrds() 
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getNumerics(ar, "sortedset", FieldCache.INT_POINT_PARSER);
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTerms(ar, "sortedset");
    });
    expectThrows(IllegalStateException.class, () -> {
        FieldCache.DEFAULT.getTermsIndex(ar, "sortedset");
    });
    expectThrows(IllegalStateException.class, () -> {
        new DocTermOrds(ar, null, "sortedset");
    });
    sortedSet = FieldCache.DEFAULT.getDocTermOrds(ar, "sortedset", null);
    assertEquals(0, sortedSet.nextDoc());
    assertEquals(0, sortedSet.nextOrd());
    assertEquals(1, sortedSet.nextOrd());
    assertEquals(SortedSetDocValues.NO_MORE_ORDS, sortedSet.nextOrd());
    assertEquals(2, sortedSet.getValueCount());
    bits = FieldCache.DEFAULT.getDocsWithField(ar, "sortedset", null);
    assertTrue(bits.get(0));
    ir.close();
    dir.close();
}
Also used : NumericDocValues(org.apache.lucene.index.NumericDocValues) LeafReader(org.apache.lucene.index.LeafReader) DirectoryReader(org.apache.lucene.index.DirectoryReader) Document(org.apache.lucene.document.Document) BinaryDocValuesField(org.apache.lucene.document.BinaryDocValuesField) BinaryDocValues(org.apache.lucene.index.BinaryDocValues) SortedDocValues(org.apache.lucene.index.SortedDocValues) NumericDocValuesField(org.apache.lucene.document.NumericDocValuesField) SortedSetDocValues(org.apache.lucene.index.SortedSetDocValues) SortedDocValuesField(org.apache.lucene.document.SortedDocValuesField) Bits(org.apache.lucene.util.Bits) SortedSetDocValuesField(org.apache.lucene.document.SortedSetDocValuesField) RandomIndexWriter(org.apache.lucene.index.RandomIndexWriter) BytesRef(org.apache.lucene.util.BytesRef) Directory(org.apache.lucene.store.Directory) IndexWriterConfig(org.apache.lucene.index.IndexWriterConfig)

Example 58 with LeafReader

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

the class TestFieldCacheWithThreads method test2.

public void test2() throws Exception {
    Random random = random();
    final int NUM_DOCS = atLeast(100);
    final Directory dir = newDirectory();
    final RandomIndexWriter writer = new RandomIndexWriter(random, dir);
    final boolean allowDups = random.nextBoolean();
    final Set<String> seen = new HashSet<>();
    if (VERBOSE) {
        System.out.println("TEST: NUM_DOCS=" + NUM_DOCS + " allowDups=" + allowDups);
    }
    int numDocs = 0;
    final List<BytesRef> docValues = new ArrayList<>();
    // TODO: deletions
    while (numDocs < NUM_DOCS) {
        final String s;
        if (random.nextBoolean()) {
            s = TestUtil.randomSimpleString(random);
        } else {
            s = TestUtil.randomUnicodeString(random);
        }
        final BytesRef br = new BytesRef(s);
        if (!allowDups) {
            if (seen.contains(s)) {
                continue;
            }
            seen.add(s);
        }
        if (VERBOSE) {
            System.out.println("  " + numDocs + ": s=" + s);
        }
        final Document doc = new Document();
        doc.add(new SortedDocValuesField("stringdv", br));
        doc.add(new NumericDocValuesField("id", numDocs));
        docValues.add(br);
        writer.addDocument(doc);
        numDocs++;
        if (random.nextInt(40) == 17) {
            // force flush
            writer.getReader().close();
        }
    }
    writer.forceMerge(1);
    final DirectoryReader r = writer.getReader();
    writer.close();
    final LeafReader sr = getOnlyLeafReader(r);
    final long END_TIME = System.nanoTime() + TimeUnit.NANOSECONDS.convert((TEST_NIGHTLY ? 30 : 1), TimeUnit.SECONDS);
    final int NUM_THREADS = TestUtil.nextInt(random(), 1, 10);
    Thread[] threads = new Thread[NUM_THREADS];
    for (int thread = 0; thread < NUM_THREADS; thread++) {
        threads[thread] = new Thread() {

            @Override
            public void run() {
                Random random = random();
                final SortedDocValues stringDVDirect;
                final NumericDocValues docIDToID;
                try {
                    stringDVDirect = sr.getSortedDocValues("stringdv");
                    docIDToID = sr.getNumericDocValues("id");
                    assertNotNull(stringDVDirect);
                } catch (IOException ioe) {
                    throw new RuntimeException(ioe);
                }
                int[] docIDToIDArray = new int[sr.maxDoc()];
                for (int i = 0; i < sr.maxDoc(); i++) {
                    try {
                        assertEquals(i, docIDToID.nextDoc());
                    } catch (IOException ioe) {
                        throw new RuntimeException(ioe);
                    }
                    try {
                        docIDToIDArray[i] = (int) docIDToID.longValue();
                    } catch (IOException ioe) {
                        throw new RuntimeException(ioe);
                    }
                }
                while (System.nanoTime() < END_TIME) {
                    for (int iter = 0; iter < 100; iter++) {
                        final int docID = random.nextInt(sr.maxDoc());
                        try {
                            SortedDocValues dvs = sr.getSortedDocValues("stringdv");
                            assertEquals(docID, dvs.advance(docID));
                            assertEquals(docValues.get(docIDToIDArray[docID]), dvs.binaryValue());
                        } catch (IOException ioe) {
                            throw new RuntimeException(ioe);
                        }
                    }
                }
            }
        };
        threads[thread].start();
    }
    for (Thread thread : threads) {
        thread.join();
    }
    r.close();
    dir.close();
}
Also used : NumericDocValues(org.apache.lucene.index.NumericDocValues) LeafReader(org.apache.lucene.index.LeafReader) DirectoryReader(org.apache.lucene.index.DirectoryReader) ArrayList(java.util.ArrayList) IOException(java.io.IOException) Document(org.apache.lucene.document.Document) SortedDocValues(org.apache.lucene.index.SortedDocValues) Random(java.util.Random) NumericDocValuesField(org.apache.lucene.document.NumericDocValuesField) SortedDocValuesField(org.apache.lucene.document.SortedDocValuesField) RandomIndexWriter(org.apache.lucene.index.RandomIndexWriter) BytesRef(org.apache.lucene.util.BytesRef) Directory(org.apache.lucene.store.Directory) HashSet(java.util.HashSet)

Example 59 with LeafReader

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

the class TestSlowCompositeReaderWrapper method testCoreListenerOnSlowCompositeReaderWrapper.

public void testCoreListenerOnSlowCompositeReaderWrapper() throws IOException {
    RandomIndexWriter w = new RandomIndexWriter(random(), newDirectory());
    final int numDocs = TestUtil.nextInt(random(), 1, 5);
    for (int i = 0; i < numDocs; ++i) {
        w.addDocument(new Document());
        if (random().nextBoolean()) {
            w.commit();
        }
    }
    w.commit();
    w.close();
    final IndexReader reader = DirectoryReader.open(w.w.getDirectory());
    final LeafReader leafReader = SlowCompositeReaderWrapper.wrap(reader);
    final int numListeners = TestUtil.nextInt(random(), 1, 10);
    final List<IndexReader.ClosedListener> listeners = new ArrayList<>();
    AtomicInteger counter = new AtomicInteger(numListeners);
    for (int i = 0; i < numListeners; ++i) {
        CountCoreListener listener = new CountCoreListener(counter, leafReader.getCoreCacheHelper().getKey());
        listeners.add(listener);
        leafReader.getCoreCacheHelper().addClosedListener(listener);
    }
    for (int i = 0; i < 100; ++i) {
        leafReader.getCoreCacheHelper().addClosedListener(listeners.get(random().nextInt(listeners.size())));
    }
    assertEquals(numListeners, counter.get());
    // make sure listeners are registered on the wrapped reader and that closing any of them has the same effect
    if (random().nextBoolean()) {
        reader.close();
    } else {
        leafReader.close();
    }
    assertEquals(0, counter.get());
    w.w.getDirectory().close();
}
Also used : LeafReader(org.apache.lucene.index.LeafReader) AtomicInteger(java.util.concurrent.atomic.AtomicInteger) IndexReader(org.apache.lucene.index.IndexReader) ArrayList(java.util.ArrayList) Document(org.apache.lucene.document.Document) RandomIndexWriter(org.apache.lucene.index.RandomIndexWriter)

Example 60 with LeafReader

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

the class UninvertDocValuesMergePolicyTest method testNonIndexedFieldDoesNonFail.

// When an non-indexed field gets merged, it exhibit the old behavior
// The field will be merged, docvalues headers updated, but no docvalues for this field
public void testNonIndexedFieldDoesNonFail() throws Exception {
    // Remove Indexed from fieldType
    removeIndexFrom(h, TEST_FIELD);
    assertU(adoc(ID_FIELD, String.valueOf(1), TEST_FIELD, String.valueOf(1)));
    assertU(commit());
    addDocValuesTo(h, TEST_FIELD);
    assertU(adoc(ID_FIELD, String.valueOf(2), TEST_FIELD, String.valueOf(2)));
    assertU(commit());
    assertU(optimize("maxSegments", "1"));
    withNewRawReader(h, topReader -> {
        assertEquals(2, topReader.numDocs());
        assertEquals(1, topReader.leaves().size());
        final FieldInfos infos = MultiFields.getMergedFieldInfos(topReader);
        assertEquals(DocValuesType.SORTED, infos.fieldInfo(TEST_FIELD).getDocValuesType());
        for (LeafReaderContext ctx : topReader.leaves()) {
            LeafReader r = ctx.reader();
            SortedDocValues docvalues = r.getSortedDocValues(TEST_FIELD);
            for (int i = 0; i < r.numDocs(); ++i) {
                Document doc = r.document(i);
                String v = doc.getField(TEST_FIELD).stringValue();
                String id = doc.getField(ID_FIELD).stringValue();
                assertEquals(DocValuesType.SORTED, r.getFieldInfos().fieldInfo(TEST_FIELD).getDocValuesType());
                assertEquals(DocValuesType.NONE, r.getFieldInfos().fieldInfo(ID_FIELD).getDocValuesType());
                if (id.equals("2")) {
                    assertTrue(docvalues.advanceExact(i));
                    assertEquals(v, docvalues.binaryValue().utf8ToString());
                } else {
                    assertFalse(docvalues.advanceExact(i));
                }
            }
        }
    });
}
Also used : FieldInfos(org.apache.lucene.index.FieldInfos) LeafReader(org.apache.lucene.index.LeafReader) LeafReaderContext(org.apache.lucene.index.LeafReaderContext) Document(org.apache.lucene.document.Document) SortedDocValues(org.apache.lucene.index.SortedDocValues)

Aggregations

LeafReader (org.apache.lucene.index.LeafReader)168 BytesRef (org.apache.lucene.util.BytesRef)65 Document (org.apache.lucene.document.Document)61 LeafReaderContext (org.apache.lucene.index.LeafReaderContext)58 Directory (org.apache.lucene.store.Directory)56 MockAnalyzer (org.apache.lucene.analysis.MockAnalyzer)55 DirectoryReader (org.apache.lucene.index.DirectoryReader)47 RandomIndexWriter (org.apache.lucene.index.RandomIndexWriter)42 Test (org.junit.Test)36 IndexWriter (org.apache.lucene.index.IndexWriter)32 Terms (org.apache.lucene.index.Terms)30 TermsEnum (org.apache.lucene.index.TermsEnum)28 NumericDocValues (org.apache.lucene.index.NumericDocValues)24 SortedSetDocValues (org.apache.lucene.index.SortedSetDocValues)24 SortedDocValues (org.apache.lucene.index.SortedDocValues)22 IndexWriterConfig (org.apache.lucene.index.IndexWriterConfig)21 IndexReader (org.apache.lucene.index.IndexReader)20 Term (org.apache.lucene.index.Term)20 SortedDocValuesField (org.apache.lucene.document.SortedDocValuesField)18 Bits (org.apache.lucene.util.Bits)18