Examples with BaseDirectoryWrapper org.apache.lucene.store.BaseDirectoryWrapper used on opensource projects

Example 16 with BaseDirectoryWrapper

use of org.apache.lucene.store.BaseDirectoryWrapper in project lucene-solr by apache.

the class TestIndexWriterExceptions method testSimulatedCorruptIndex2.

// Simulate a corrupt index by removing one of the
// files and make sure we get an IOException trying to
// open the index:
public void testSimulatedCorruptIndex2() throws IOException {
    BaseDirectoryWrapper dir = newDirectory();
    // we are corrupting it!
    dir.setCheckIndexOnClose(false);
    IndexWriter writer = null;
    writer = new IndexWriter(dir, newIndexWriterConfig(new MockAnalyzer(random())).setMergePolicy(newLogMergePolicy(true)).setUseCompoundFile(true));
    MergePolicy lmp = writer.getConfig().getMergePolicy();
    // Force creation of CFS:
    lmp.setNoCFSRatio(1.0);
    lmp.setMaxCFSSegmentSizeMB(Double.POSITIVE_INFINITY);
    // add 100 documents
    for (int i = 0; i < 100; i++) {
        addDoc(writer);
    }
    // close
    writer.close();
    long gen = SegmentInfos.getLastCommitGeneration(dir);
    assertTrue("segment generation should be > 0 but got " + gen, gen > 0);
    boolean corrupted = false;
    SegmentInfos sis = SegmentInfos.readLatestCommit(dir);
    for (SegmentCommitInfo si : sis) {
        assertTrue(si.info.getUseCompoundFile());
        List<String> victims = new ArrayList<String>(si.info.files());
        Collections.shuffle(victims, random());
        dir.deleteFile(victims.get(0));
        corrupted = true;
        break;
    }
    assertTrue("failed to find cfs file to remove: ", corrupted);
    expectThrows(Exception.class, () -> {
        DirectoryReader.open(dir);
    });
    dir.close();
}

Example 17 with BaseDirectoryWrapper

use of org.apache.lucene.store.BaseDirectoryWrapper in project lucene-solr by apache.

the class TestFilterLeafReader method testFilterIndexReader.

/**
   * Tests the IndexReader.getFieldNames implementation
   * @throws Exception on error
   */
public void testFilterIndexReader() throws Exception {
    Directory directory = newDirectory();
    IndexWriter writer = new IndexWriter(directory, newIndexWriterConfig(new MockAnalyzer(random())));
    Document d1 = new Document();
    d1.add(newTextField("default", "one two", Field.Store.YES));
    writer.addDocument(d1);
    Document d2 = new Document();
    d2.add(newTextField("default", "one three", Field.Store.YES));
    writer.addDocument(d2);
    Document d3 = new Document();
    d3.add(newTextField("default", "two four", Field.Store.YES));
    writer.addDocument(d3);
    writer.forceMerge(1);
    writer.close();
    Directory target = newDirectory();
    // We mess with the postings so this can fail:
    ((BaseDirectoryWrapper) target).setCrossCheckTermVectorsOnClose(false);
    writer = new IndexWriter(target, newIndexWriterConfig(new MockAnalyzer(random())));
    try (LeafReader reader = new TestReader(getOnlyLeafReader(DirectoryReader.open(directory)))) {
        writer.addIndexes(SlowCodecReaderWrapper.wrap(reader));
    }
    writer.close();
    IndexReader reader = DirectoryReader.open(target);
    TermsEnum terms = MultiFields.getTerms(reader, "default").iterator();
    while (terms.next() != null) {
        assertTrue(terms.term().utf8ToString().indexOf('e') != -1);
    }
    assertEquals(TermsEnum.SeekStatus.FOUND, terms.seekCeil(new BytesRef("one")));
    PostingsEnum positions = terms.postings(null, PostingsEnum.ALL);
    while (positions.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
        assertTrue((positions.docID() % 2) == 1);
    }
    reader.close();
    directory.close();
    target.close();
}

Example 18 with BaseDirectoryWrapper

use of org.apache.lucene.store.BaseDirectoryWrapper in project lucene-solr by apache.

the class TestSwappedIndexFiles method swapOneFile.

private void swapOneFile(Directory dir1, Directory dir2, String victim) throws IOException {
    if (VERBOSE) {
        System.out.println("TEST: swap file " + victim);
    }
    try (BaseDirectoryWrapper dirCopy = newDirectory()) {
        dirCopy.setCheckIndexOnClose(false);
        // Copy all files from dir1 to dirCopy, except victim which we copy from dir2:
        for (String name : dir1.listAll()) {
            if (name.equals(victim) == false) {
                dirCopy.copyFrom(dir1, name, name, IOContext.DEFAULT);
            } else {
                dirCopy.copyFrom(dir2, name, name, IOContext.DEFAULT);
            }
            dirCopy.sync(Collections.singleton(name));
        }
        try {
            // NOTE: we .close so that if the test fails (truncation not detected) we don't also get all these confusing errors about open files:
            DirectoryReader.open(dirCopy).close();
            fail("wrong file " + victim + " not detected");
        } catch (CorruptIndexException | EOFException | IndexFormatTooOldException e) {
        // expected
        }
        // CheckIndex should also fail:
        try {
            TestUtil.checkIndex(dirCopy, true, true, null);
            fail("wrong file " + victim + " not detected");
        } catch (CorruptIndexException | EOFException | IndexFormatTooOldException e) {
        // expected
        }
    }
}

Example 19 with BaseDirectoryWrapper

use of org.apache.lucene.store.BaseDirectoryWrapper in project lucene-solr by apache.

the class TestPagedBytes method testOverflow.

// memory hole
@Ignore
public void testOverflow() throws IOException {
    BaseDirectoryWrapper dir = newFSDirectory(createTempDir("testOverflow"));
    if (dir instanceof MockDirectoryWrapper) {
        ((MockDirectoryWrapper) dir).setThrottling(MockDirectoryWrapper.Throttling.NEVER);
    }
    final int blockBits = TestUtil.nextInt(random(), 14, 28);
    final int blockSize = 1 << blockBits;
    byte[] arr = new byte[TestUtil.nextInt(random(), blockSize / 2, blockSize * 2)];
    for (int i = 0; i < arr.length; ++i) {
        arr[i] = (byte) i;
    }
    final long numBytes = (1L << 31) + TestUtil.nextInt(random(), 1, blockSize * 3);
    final PagedBytes p = new PagedBytes(blockBits);
    final IndexOutput out = dir.createOutput("foo", IOContext.DEFAULT);
    for (long i = 0; i < numBytes; ) {
        assertEquals(i, out.getFilePointer());
        final int len = (int) Math.min(arr.length, numBytes - i);
        out.writeBytes(arr, len);
        i += len;
    }
    assertEquals(numBytes, out.getFilePointer());
    out.close();
    final IndexInput in = dir.openInput("foo", IOContext.DEFAULT);
    p.copy(in, numBytes);
    final PagedBytes.Reader reader = p.freeze(random().nextBoolean());
    for (long offset : new long[] { 0L, Integer.MAX_VALUE, numBytes - 1, TestUtil.nextLong(random(), 1, numBytes - 2) }) {
        BytesRef b = new BytesRef();
        reader.fillSlice(b, offset, 1);
        assertEquals(arr[(int) (offset % arr.length)], b.bytes[b.offset]);
    }
    in.close();
    dir.close();
}

Example 20 with BaseDirectoryWrapper

use of org.apache.lucene.store.BaseDirectoryWrapper in project lucene-solr by apache.

the class ThreadedIndexingAndSearchingTestCase method runTest.

public void runTest(String testName) throws Exception {
    failed.set(false);
    addCount.set(0);
    delCount.set(0);
    packCount.set(0);
    final long t0 = System.currentTimeMillis();
    Random random = new Random(random().nextLong());
    final LineFileDocs docs = new LineFileDocs(random);
    final Path tempDir = createTempDir(testName);
    // some subclasses rely on this being MDW
    dir = getDirectory(newMockFSDirectory(tempDir));
    if (dir instanceof BaseDirectoryWrapper) {
        // don't double-checkIndex, we do it ourselves.
        ((BaseDirectoryWrapper) dir).setCheckIndexOnClose(false);
    }
    MockAnalyzer analyzer = new MockAnalyzer(random());
    analyzer.setMaxTokenLength(TestUtil.nextInt(random(), 1, IndexWriter.MAX_TERM_LENGTH));
    final IndexWriterConfig conf = newIndexWriterConfig(analyzer).setCommitOnClose(false);
    conf.setInfoStream(new FailOnNonBulkMergesInfoStream());
    if (conf.getMergePolicy() instanceof MockRandomMergePolicy) {
        ((MockRandomMergePolicy) conf.getMergePolicy()).setDoNonBulkMerges(false);
    }
    if (LuceneTestCase.TEST_NIGHTLY) {
        // newIWConfig makes smallish max seg size, which
        // results in tons and tons of segments for this test
        // when run nightly:
        MergePolicy mp = conf.getMergePolicy();
        if (mp instanceof TieredMergePolicy) {
            ((TieredMergePolicy) mp).setMaxMergedSegmentMB(5000.);
        } else if (mp instanceof LogByteSizeMergePolicy) {
            ((LogByteSizeMergePolicy) mp).setMaxMergeMB(1000.);
        } else if (mp instanceof LogMergePolicy) {
            ((LogMergePolicy) mp).setMaxMergeDocs(100000);
        }
        // when running nightly, merging can still have crazy parameters, 
        // and might use many per-field codecs. turn on CFS for IW flushes
        // and ensure CFS ratio is reasonable to keep it contained.
        conf.setUseCompoundFile(true);
        mp.setNoCFSRatio(Math.max(0.25d, mp.getNoCFSRatio()));
    }
    conf.setMergedSegmentWarmer(new IndexWriter.IndexReaderWarmer() {

        @Override
        public void warm(LeafReader reader) throws IOException {
            if (VERBOSE) {
                System.out.println("TEST: now warm merged reader=" + reader);
            }
            warmed.put(((SegmentReader) reader).core, Boolean.TRUE);
            final int maxDoc = reader.maxDoc();
            final Bits liveDocs = reader.getLiveDocs();
            int sum = 0;
            final int inc = Math.max(1, maxDoc / 50);
            for (int docID = 0; docID < maxDoc; docID += inc) {
                if (liveDocs == null || liveDocs.get(docID)) {
                    final Document doc = reader.document(docID);
                    sum += doc.getFields().size();
                }
            }
            IndexSearcher searcher = newSearcher(reader, false);
            sum += searcher.search(new TermQuery(new Term("body", "united")), 10).totalHits;
            if (VERBOSE) {
                System.out.println("TEST: warm visited " + sum + " fields");
            }
        }
    });
    if (VERBOSE) {
        conf.setInfoStream(new PrintStreamInfoStream(System.out) {

            @Override
            public void message(String component, String message) {
                if ("TP".equals(component)) {
                    // ignore test points!
                    return;
                }
                super.message(component, message);
            }
        });
    }
    writer = new IndexWriter(dir, conf);
    TestUtil.reduceOpenFiles(writer);
    final ExecutorService es = random().nextBoolean() ? null : Executors.newCachedThreadPool(new NamedThreadFactory(testName));
    doAfterWriter(es);
    final int NUM_INDEX_THREADS = TestUtil.nextInt(random(), 2, 4);
    final int RUN_TIME_SEC = LuceneTestCase.TEST_NIGHTLY ? 300 : RANDOM_MULTIPLIER;
    final Set<String> delIDs = Collections.synchronizedSet(new HashSet<String>());
    final Set<String> delPackIDs = Collections.synchronizedSet(new HashSet<String>());
    final List<SubDocs> allSubDocs = Collections.synchronizedList(new ArrayList<SubDocs>());
    final long stopTime = System.currentTimeMillis() + RUN_TIME_SEC * 1000;
    final Thread[] indexThreads = launchIndexingThreads(docs, NUM_INDEX_THREADS, stopTime, delIDs, delPackIDs, allSubDocs);
    if (VERBOSE) {
        System.out.println("TEST: DONE start " + NUM_INDEX_THREADS + " indexing threads [" + (System.currentTimeMillis() - t0) + " ms]");
    }
    // Let index build up a bit
    Thread.sleep(100);
    doSearching(es, stopTime);
    if (VERBOSE) {
        System.out.println("TEST: all searching done [" + (System.currentTimeMillis() - t0) + " ms]");
    }
    for (Thread thread : indexThreads) {
        thread.join();
    }
    if (VERBOSE) {
        System.out.println("TEST: done join indexing threads [" + (System.currentTimeMillis() - t0) + " ms]; addCount=" + addCount + " delCount=" + delCount);
    }
    final IndexSearcher s = getFinalSearcher();
    if (VERBOSE) {
        System.out.println("TEST: finalSearcher=" + s);
    }
    assertFalse(failed.get());
    boolean doFail = false;
    // Verify: make sure delIDs are in fact deleted:
    for (String id : delIDs) {
        final TopDocs hits = s.search(new TermQuery(new Term("docid", id)), 1);
        if (hits.totalHits != 0) {
            System.out.println("doc id=" + id + " is supposed to be deleted, but got " + hits.totalHits + " hits; first docID=" + hits.scoreDocs[0].doc);
            doFail = true;
        }
    }
    // Verify: make sure delPackIDs are in fact deleted:
    for (String id : delPackIDs) {
        final TopDocs hits = s.search(new TermQuery(new Term("packID", id)), 1);
        if (hits.totalHits != 0) {
            System.out.println("packID=" + id + " is supposed to be deleted, but got " + hits.totalHits + " matches");
            doFail = true;
        }
    }
    // Verify: make sure each group of sub-docs are still in docID order:
    for (SubDocs subDocs : allSubDocs) {
        TopDocs hits = s.search(new TermQuery(new Term("packID", subDocs.packID)), 20);
        if (!subDocs.deleted) {
            // We sort by relevance but the scores should be identical so sort falls back to by docID:
            if (hits.totalHits != subDocs.subIDs.size()) {
                System.out.println("packID=" + subDocs.packID + ": expected " + subDocs.subIDs.size() + " hits but got " + hits.totalHits);
                doFail = true;
            } else {
                int lastDocID = -1;
                int startDocID = -1;
                for (ScoreDoc scoreDoc : hits.scoreDocs) {
                    final int docID = scoreDoc.doc;
                    if (lastDocID != -1) {
                        assertEquals(1 + lastDocID, docID);
                    } else {
                        startDocID = docID;
                    }
                    lastDocID = docID;
                    final Document doc = s.doc(docID);
                    assertEquals(subDocs.packID, doc.get("packID"));
                }
                lastDocID = startDocID - 1;
                for (String subID : subDocs.subIDs) {
                    hits = s.search(new TermQuery(new Term("docid", subID)), 1);
                    assertEquals(1, hits.totalHits);
                    final int docID = hits.scoreDocs[0].doc;
                    if (lastDocID != -1) {
                        assertEquals(1 + lastDocID, docID);
                    }
                    lastDocID = docID;
                }
            }
        } else {
            // because we can re-use packID for update:
            for (String subID : subDocs.subIDs) {
                assertEquals(0, s.search(new TermQuery(new Term("docid", subID)), 1).totalHits);
            }
        }
    }
    // Verify: make sure all not-deleted docs are in fact
    // not deleted:
    final int endID = Integer.parseInt(docs.nextDoc().get("docid"));
    docs.close();
    for (int id = 0; id < endID; id++) {
        String stringID = "" + id;
        if (!delIDs.contains(stringID)) {
            final TopDocs hits = s.search(new TermQuery(new Term("docid", stringID)), 1);
            if (hits.totalHits != 1) {
                System.out.println("doc id=" + stringID + " is not supposed to be deleted, but got hitCount=" + hits.totalHits + "; delIDs=" + delIDs);
                doFail = true;
            }
        }
    }
    assertFalse(doFail);
    assertEquals("index=" + writer.segString() + " addCount=" + addCount + " delCount=" + delCount, addCount.get() - delCount.get(), s.getIndexReader().numDocs());
    releaseSearcher(s);
    writer.commit();
    assertEquals("index=" + writer.segString() + " addCount=" + addCount + " delCount=" + delCount, addCount.get() - delCount.get(), writer.numDocs());
    doClose();
    try {
        writer.commit();
    } finally {
        writer.close();
    }
    // searches, and that IS may be using this es!
    if (es != null) {
        es.shutdown();
        es.awaitTermination(1, TimeUnit.SECONDS);
    }
    TestUtil.checkIndex(dir);
    dir.close();
    if (VERBOSE) {
        System.out.println("TEST: done [" + (System.currentTimeMillis() - t0) + " ms]");
    }
}