public void testNRTAndCommit() throws Exception {
Directory dir = newDirectory();
NRTCachingDirectory cachedDir = new NRTCachingDirectory(dir, 2.0, 25.0);
MockAnalyzer analyzer = new MockAnalyzer(random());
analyzer.setMaxTokenLength(TestUtil.nextInt(random(), 1, IndexWriter.MAX_TERM_LENGTH));
IndexWriterConfig conf = newIndexWriterConfig(analyzer);
RandomIndexWriter w = new RandomIndexWriter(random(), cachedDir, conf);
final LineFileDocs docs = new LineFileDocs(random(), true);
final int numDocs = TestUtil.nextInt(random(), 100, 400);
if (VERBOSE) {
System.out.println("TEST: numDocs=" + numDocs);
}
final List<BytesRef> ids = new ArrayList<>();
DirectoryReader r = null;
for (int docCount = 0; docCount < numDocs; docCount++) {
final Document doc = docs.nextDoc();
ids.add(new BytesRef(doc.get("docid")));
w.addDocument(doc);
if (random().nextInt(20) == 17) {
if (r == null) {
r = DirectoryReader.open(w.w);
} else {
final DirectoryReader r2 = DirectoryReader.openIfChanged(r);
if (r2 != null) {
r.close();
r = r2;
}
}
assertEquals(1 + docCount, r.numDocs());
final IndexSearcher s = newSearcher(r);
// Just make sure search can run; we can't assert
// totHits since it could be 0
TopDocs hits = s.search(new TermQuery(new Term("body", "the")), 10);
// System.out.println("tot hits " + hits.totalHits);
}
}
if (r != null) {
r.close();
}
// Close should force cache to clear since all files are sync'd
w.close();
final String[] cachedFiles = cachedDir.listCachedFiles();
for (String file : cachedFiles) {
System.out.println("FAIL: cached file " + file + " remains after sync");
}
assertEquals(0, cachedFiles.length);
r = DirectoryReader.open(dir);
for (BytesRef id : ids) {
assertEquals(1, r.docFreq(new Term("docid", id)));
}
r.close();
cachedDir.close();
docs.close();
}
public void testDuellMemIndex() throws IOException {
LineFileDocs lineFileDocs = new LineFileDocs(random());
int numDocs = atLeast(10);
MemoryIndex memory = randomMemoryIndex();
for (int i = 0; i < numDocs; i++) {
Directory dir = newDirectory();
MockAnalyzer mockAnalyzer = new MockAnalyzer(random());
mockAnalyzer.setMaxTokenLength(TestUtil.nextInt(random(), 1, IndexWriter.MAX_TERM_LENGTH));
IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(random(), mockAnalyzer));
Document nextDoc = lineFileDocs.nextDoc();
Document doc = new Document();
for (IndexableField field : nextDoc.getFields()) {
if (field.fieldType().indexOptions() != IndexOptions.NONE) {
doc.add(field);
if (random().nextInt(3) == 0) {
doc.add(field); // randomly add the same field twice
}
}
}
writer.addDocument(doc);
writer.close();
for (IndexableField field : doc) {
memory.addField(field.name(), ((Field) field).stringValue(), mockAnalyzer);
}
DirectoryReader competitor = DirectoryReader.open(dir);
LeafReader memIndexReader = (LeafReader) memory.createSearcher().getIndexReader();
TestUtil.checkReader(memIndexReader);
duellReaders(competitor, memIndexReader);
IOUtils.close(competitor, memIndexReader);
memory.reset();
dir.close();
}
lineFileDocs.close();
}
public void test() throws Exception {
final Directory d = newDirectory();
MockAnalyzer analyzer = new MockAnalyzer(random());
analyzer.setMaxTokenLength(TestUtil.nextInt(random(), 1, IndexWriter.MAX_TERM_LENGTH));
final MyIndexWriter w =
new MyIndexWriter(d, newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
// Try to make an index that requires merging:
w.getConfig().setMaxBufferedDocs(TestUtil.nextInt(random(), 2, 11));
final int numStartDocs = atLeast(20);
final LineFileDocs docs = new LineFileDocs(random(), true);
for (int docIDX = 0; docIDX < numStartDocs; docIDX++) {
w.addDocument(docs.nextDoc());
}
MergePolicy mp = w.getConfig().getMergePolicy();
final int mergeAtOnce = 1 + w.segmentInfos.size();
if (mp instanceof TieredMergePolicy) {
((TieredMergePolicy) mp).setMaxMergeAtOnce(mergeAtOnce);
} else if (mp instanceof LogMergePolicy) {
((LogMergePolicy) mp).setMergeFactor(mergeAtOnce);
} else {
// skip test
w.close();
d.close();
return;
}
final AtomicBoolean doStop = new AtomicBoolean();
w.getConfig().setMaxBufferedDocs(2);
Thread t =
new Thread() {
@Override
public void run() {
try {
while (!doStop.get()) {
w.updateDocument(
new Term("docid", "" + random().nextInt(numStartDocs)), docs.nextDoc());
// Force deletes to apply
w.getReader().close();
}
} catch (Throwable t) {
throw new RuntimeException(t);
}
}
};
t.start();
w.forceMerge(1);
doStop.set(true);
t.join();
assertTrue("merge count is " + w.mergeCount.get(), w.mergeCount.get() <= 1);
w.close();
d.close();
docs.close();
}
// make sure we never reuse from another reader even if it is the same field & codec etc
public void testReuseDocsEnumDifferentReader() throws IOException {
Directory dir = newDirectory();
Codec cp = TestUtil.alwaysPostingsFormat(new Lucene40RWPostingsFormat());
MockAnalyzer analyzer = new MockAnalyzer(random());
analyzer.setMaxTokenLength(TestUtil.nextInt(random(), 1, IndexWriter.MAX_TERM_LENGTH));
RandomIndexWriter writer =
new RandomIndexWriter(random(), dir, newIndexWriterConfig(analyzer).setCodec(cp));
int numdocs = atLeast(20);
createRandomIndex(numdocs, writer, random());
writer.commit();
DirectoryReader firstReader = DirectoryReader.open(dir);
DirectoryReader secondReader = DirectoryReader.open(dir);
List<LeafReaderContext> leaves = firstReader.leaves();
List<LeafReaderContext> leaves2 = secondReader.leaves();
for (LeafReaderContext ctx : leaves) {
Terms terms = ctx.reader().terms("body");
TermsEnum iterator = terms.iterator();
IdentityHashMap<PostingsEnum, Boolean> enums = new IdentityHashMap<>();
MatchNoBits bits = new Bits.MatchNoBits(firstReader.maxDoc());
iterator = terms.iterator();
PostingsEnum docs = null;
BytesRef term = null;
while ((term = iterator.next()) != null) {
docs =
iterator.postings(
null,
randomDocsEnum("body", term, leaves2, bits),
random().nextBoolean() ? PostingsEnum.FREQS : PostingsEnum.NONE);
enums.put(docs, true);
}
assertEquals(terms.size(), enums.size());
iterator = terms.iterator();
enums.clear();
docs = null;
while ((term = iterator.next()) != null) {
docs =
iterator.postings(
bits,
randomDocsEnum("body", term, leaves2, bits),
random().nextBoolean() ? PostingsEnum.FREQS : PostingsEnum.NONE);
enums.put(docs, true);
}
assertEquals(terms.size(), enums.size());
}
writer.close();
IOUtils.close(firstReader, secondReader, dir);
}
public void testDuelMemoryIndexCoreDirectoryWithArrayField() throws Exception {
final String field_name = "text";
MockAnalyzer mockAnalyzer = new MockAnalyzer(random());
if (random().nextBoolean()) {
mockAnalyzer.setOffsetGap(random().nextInt(100));
}
// index into a random directory
FieldType type = new FieldType(TextField.TYPE_STORED);
type.setStoreTermVectorOffsets(true);
type.setStoreTermVectorPayloads(false);
type.setStoreTermVectorPositions(true);
type.setStoreTermVectors(true);
type.freeze();
Document doc = new Document();
doc.add(new Field(field_name, "la la", type));
doc.add(new Field(field_name, "foo bar foo bar foo", type));
Directory dir = newDirectory();
IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(random(), mockAnalyzer));
writer.updateDocument(new Term("id", "1"), doc);
writer.commit();
writer.close();
DirectoryReader reader = DirectoryReader.open(dir);
// Index document in Memory index
MemoryIndex memIndex = new MemoryIndex(true);
memIndex.addField(field_name, "la la", mockAnalyzer);
memIndex.addField(field_name, "foo bar foo bar foo", mockAnalyzer);
// compare term vectors
Terms ramTv = reader.getTermVector(0, field_name);
IndexReader memIndexReader = memIndex.createSearcher().getIndexReader();
TestUtil.checkReader(memIndexReader);
Terms memTv = memIndexReader.getTermVector(0, field_name);
compareTermVectors(ramTv, memTv, field_name);
memIndexReader.close();
reader.close();
dir.close();
}
public void testSameFieldAddedMultipleTimes() throws IOException {
MemoryIndex mindex = randomMemoryIndex();
MockAnalyzer mockAnalyzer = new MockAnalyzer(random());
mindex.addField("field", "the quick brown fox", mockAnalyzer);
mindex.addField("field", "jumps over the", mockAnalyzer);
LeafReader reader = (LeafReader) mindex.createSearcher().getIndexReader();
TestUtil.checkReader(reader);
assertEquals(7, reader.terms("field").getSumTotalTermFreq());
PhraseQuery query = new PhraseQuery("field", "fox", "jumps");
assertTrue(mindex.search(query) > 0.1);
mindex.reset();
mockAnalyzer.setPositionIncrementGap(1 + random().nextInt(10));
mindex.addField("field", "the quick brown fox", mockAnalyzer);
mindex.addField("field", "jumps over the", mockAnalyzer);
assertEquals(0, mindex.search(query), 0.00001f);
query = new PhraseQuery(10, "field", "fox", "jumps");
assertTrue(
"posGap" + mockAnalyzer.getPositionIncrementGap("field"), mindex.search(query) > 0.0001);
TestUtil.checkReader(mindex.createSearcher().getIndexReader());
}
@Test
public void testRollingUpdates() throws Exception {
Random random = new Random(random().nextLong());
final BaseDirectoryWrapper dir = newDirectory();
// test checks for no unref'ed files with the IW helper method, which isn't aware of "tried to
// delete files"
if (dir instanceof MockDirectoryWrapper) {
((MockDirectoryWrapper) dir).setEnableVirusScanner(false);
}
final LineFileDocs docs = new LineFileDocs(random, true);
// provider.register(new MemoryCodec());
if (random().nextBoolean()) {
Codec.setDefault(
TestUtil.alwaysPostingsFormat(
new MemoryPostingsFormat(random().nextBoolean(), random.nextFloat())));
}
MockAnalyzer analyzer = new MockAnalyzer(random());
analyzer.setMaxTokenLength(TestUtil.nextInt(random(), 1, IndexWriter.MAX_TERM_LENGTH));
final IndexWriter w = new IndexWriter(dir, newIndexWriterConfig(analyzer));
final int SIZE = atLeast(20);
int id = 0;
IndexReader r = null;
IndexSearcher s = null;
final int numUpdates =
(int)
(SIZE * (2 + (TEST_NIGHTLY ? 200 * random().nextDouble() : 5 * random().nextDouble())));
if (VERBOSE) {
System.out.println("TEST: numUpdates=" + numUpdates);
}
int updateCount = 0;
// TODO: sometimes update ids not in order...
for (int docIter = 0; docIter < numUpdates; docIter++) {
final Document doc = docs.nextDoc();
final String myID = Integer.toString(id);
if (id == SIZE - 1) {
id = 0;
} else {
id++;
}
if (VERBOSE) {
System.out.println(" docIter=" + docIter + " id=" + id);
}
((Field) doc.getField("docid")).setStringValue(myID);
Term idTerm = new Term("docid", myID);
final boolean doUpdate;
if (s != null && updateCount < SIZE) {
TopDocs hits = s.search(new TermQuery(idTerm), 1);
assertEquals(1, hits.totalHits);
doUpdate = !w.tryDeleteDocument(r, hits.scoreDocs[0].doc);
if (VERBOSE) {
if (doUpdate) {
System.out.println(" tryDeleteDocument failed");
} else {
System.out.println(" tryDeleteDocument succeeded");
}
}
} else {
doUpdate = true;
if (VERBOSE) {
System.out.println(" no searcher: doUpdate=true");
}
}
updateCount++;
if (doUpdate) {
if (random().nextBoolean()) {
w.updateDocument(idTerm, doc);
} else {
// It's OK to not be atomic for this test (no separate thread reopening readers):
w.deleteDocuments(new TermQuery(idTerm));
w.addDocument(doc);
}
} else {
w.addDocument(doc);
}
if (docIter >= SIZE && random().nextInt(50) == 17) {
if (r != null) {
r.close();
}
final boolean applyDeletions = random().nextBoolean();
if (VERBOSE) {
System.out.println("TEST: reopen applyDeletions=" + applyDeletions);
}
r = w.getReader(applyDeletions);
if (applyDeletions) {
s = newSearcher(r);
} else {
s = null;
}
assertTrue(
"applyDeletions=" + applyDeletions + " r.numDocs()=" + r.numDocs() + " vs SIZE=" + SIZE,
!applyDeletions || r.numDocs() == SIZE);
updateCount = 0;
}
}
if (r != null) {
r.close();
}
w.commit();
assertEquals(SIZE, w.numDocs());
w.close();
TestIndexWriter.assertNoUnreferencedFiles(dir, "leftover files after rolling updates");
docs.close();
// LUCENE-4455:
SegmentInfos infos = SegmentInfos.readLatestCommit(dir);
long totalBytes = 0;
for (SegmentCommitInfo sipc : infos) {
totalBytes += sipc.sizeInBytes();
}
long totalBytes2 = 0;
for (String fileName : dir.listAll()) {
if (IndexFileNames.CODEC_FILE_PATTERN.matcher(fileName).matches()) {
totalBytes2 += dir.fileLength(fileName);
}
}
assertEquals(totalBytes2, totalBytes);
dir.close();
}
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, true);
final Path tempDir = createTempDir(testName);
dir = getDirectory(newMockFSDirectory(tempDir)); // some subclasses rely on this being MDW
if (dir instanceof BaseDirectoryWrapper) {
((BaseDirectoryWrapper) dir)
.setCheckIndexOnClose(false); // don't double-checkIndex, we do it ourselves.
}
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);
}
}
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 StoredDocument doc = reader.document(docID);
sum += doc.getFields().size();
}
}
IndexSearcher searcher = newSearcher(reader);
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)) {
return; // ignore test points!
}
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 (int thread = 0; thread < indexThreads.length; 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 StoredDocument 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 {
// Pack was deleted -- make sure its docs are
// deleted. We can't verify packID is deleted
// 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();
}
// Cannot close until after writer is closed because
// writer has merged segment warmer that uses IS to run
// searches, and that IS may be using this es!
if (es != null) {
es.shutdown();
es.awaitTermination(1, TimeUnit.SECONDS);
}
TestUtil.checkIndex(dir);
dir.close();
IOUtils.rm(tempDir);
if (VERBOSE) {
System.out.println("TEST: done [" + (System.currentTimeMillis() - t0) + " ms]");
}
}