public TermVectorsWriter(Directory directory, String segment, FieldInfos fieldInfos)
throws IOException {
// Open files for TermVector storage
tvx = directory.createOutput(segment + TVX_EXTENSION);
tvx.writeInt(FORMAT_VERSION);
tvd = directory.createOutput(segment + TVD_EXTENSION);
tvd.writeInt(FORMAT_VERSION);
tvf = directory.createOutput(segment + TVF_EXTENSION);
tvf.writeInt(FORMAT_VERSION);
this.fieldInfos = fieldInfos;
fields = new Vector(fieldInfos.size());
terms = new Vector();
}
public void writeChecksums() throws IOException {
String checksumName = CHECKSUMS_PREFIX + System.currentTimeMillis();
ImmutableMap<String, StoreFileMetaData> files = list();
synchronized (mutex) {
Map<String, String> checksums = new HashMap<String, String>();
for (StoreFileMetaData metaData : files.values()) {
if (metaData.checksum() != null) {
checksums.put(metaData.name(), metaData.checksum());
}
}
IndexOutput output = directory.createOutput(checksumName, IOContext.DEFAULT, true);
output.writeInt(0); // version
output.writeStringStringMap(checksums);
output.close();
}
for (StoreFileMetaData metaData : files.values()) {
if (metaData.name().startsWith(CHECKSUMS_PREFIX) && !checksumName.equals(metaData.name())) {
try {
directory.deleteFileChecksum(metaData.name());
} catch (Exception e) {
// ignore
}
}
}
}
@Override
protected void finishInternal(int docCount) throws IOException {
final int numValues = hash.size();
final IndexOutput datOut = getOrCreateDataOut();
datOut.writeInt(size);
if (size != -1) {
final BytesRef bytesRef = new BytesRef(size);
for (int i = 0; i < numValues; i++) {
hash.get(i, bytesRef);
datOut.writeBytes(bytesRef.bytes, bytesRef.offset, bytesRef.length);
}
}
final IndexOutput idxOut = getOrCreateIndexOut();
idxOut.writeInt(numValues);
writeIndex(idxOut, docCount, numValues, docToEntry);
}
final void finishCommit(Directory dir) throws IOException {
if (pendingSegnOutput == null) throw new IllegalStateException("prepareCommit was not called");
boolean success = false;
try {
pendingSegnOutput.finishCommit();
pendingSegnOutput.close();
pendingSegnOutput = null;
success = true;
} finally {
if (!success) rollbackCommit(dir);
}
// NOTE: if we crash here, we have left a segments_N
// file in the directory in a possibly corrupt state (if
// some bytes made it to stable storage and others
// didn't). But, the segments_N file includes checksum
// at the end, which should catch this case. So when a
// reader tries to read it, it will throw a
// CorruptIndexException, which should cause the retry
// logic in SegmentInfos to kick in and load the last
// good (previous) segments_N-1 file.
final String fileName =
IndexFileNames.fileNameFromGeneration(IndexFileNames.SEGMENTS, "", generation);
success = false;
try {
dir.sync(Collections.singleton(fileName));
success = true;
} finally {
if (!success) {
try {
dir.deleteFile(fileName);
} catch (Throwable t) {
// Suppress so we keep throwing the original exception
}
}
}
lastGeneration = generation;
try {
IndexOutput genOutput = dir.createOutput(IndexFileNames.SEGMENTS_GEN);
try {
genOutput.writeInt(FORMAT_LOCKLESS);
genOutput.writeLong(generation);
genOutput.writeLong(generation);
} finally {
genOutput.close();
}
} catch (ThreadInterruptedException t) {
throw t;
} catch (Throwable t) {
// It's OK if we fail to write this file since it's
// used only as one of the retry fallbacks.
}
}
private void insertData(ByteBufferDirectory dir, int bufferSizeInBytes) throws IOException {
byte[] test = new byte[] {1, 2, 3, 4, 5, 6, 7, 8};
IndexOutput indexOutput = dir.createOutput("value1", IOContext.DEFAULT);
indexOutput.writeBytes(new byte[] {2, 4, 6, 7, 8}, 5);
indexOutput.writeInt(-1);
indexOutput.writeLong(10);
indexOutput.writeInt(0);
indexOutput.writeInt(0);
indexOutput.writeBytes(test, 8);
indexOutput.writeBytes(test, 5);
indexOutput.seek(0);
indexOutput.writeByte((byte) 8);
if (bufferSizeInBytes > 4) {
indexOutput.seek(2);
indexOutput.writeBytes(new byte[] {1, 2}, 2);
}
indexOutput.close();
}
private void insertData(CoherenceDirectory dir, String fileName) throws IOException {
byte[] test = new byte[] {1, 2, 3, 4, 5, 6, 7, 8};
IndexOutput indexOutput = dir.createOutput(fileName);
indexOutput.writeBytes(new byte[] {2, 4, 6, 7, 8}, 5);
indexOutput.writeInt(-1);
indexOutput.writeLong(10);
indexOutput.writeInt(0);
indexOutput.writeInt(0);
indexOutput.writeBytes(test, 8);
indexOutput.writeBytes(test, 5);
indexOutput.seek(0);
indexOutput.writeByte((byte) 8);
if (dir.getBucketSize() > 4) {
indexOutput.seek(2);
indexOutput.writeBytes(new byte[] {1, 2}, 2);
}
indexOutput.close();
}
@Override
public void close() throws IOException {
delegateFieldsConsumer.close();
// Now we are done accumulating values for these fields
List<Entry<FieldInfo, FuzzySet>> nonSaturatedBlooms =
new ArrayList<Map.Entry<FieldInfo, FuzzySet>>();
for (Entry<FieldInfo, FuzzySet> entry : bloomFilters.entrySet()) {
FuzzySet bloomFilter = entry.getValue();
if (!bloomFilterFactory.isSaturated(bloomFilter, entry.getKey())) {
nonSaturatedBlooms.add(entry);
}
}
String bloomFileName =
IndexFileNames.segmentFileName(
state.segmentInfo.name, state.segmentSuffix, BLOOM_EXTENSION);
IndexOutput bloomOutput = null;
try {
bloomOutput = state.directory.createOutput(bloomFileName, state.context);
CodecUtil.writeHeader(bloomOutput, BLOOM_CODEC_NAME, BLOOM_CODEC_VERSION);
// remember the name of the postings format we will delegate to
bloomOutput.writeString(delegatePostingsFormat.getName());
// First field in the output file is the number of fields+blooms saved
bloomOutput.writeInt(nonSaturatedBlooms.size());
for (Entry<FieldInfo, FuzzySet> entry : nonSaturatedBlooms) {
FieldInfo fieldInfo = entry.getKey();
FuzzySet bloomFilter = entry.getValue();
bloomOutput.writeInt(fieldInfo.number);
saveAppropriatelySizedBloomFilter(bloomOutput, bloomFilter, fieldInfo);
}
} finally {
IOUtils.close(bloomOutput);
}
// We are done with large bitsets so no need to keep them hanging around
bloomFilters.clear();
}
@Override
public void writeInt(int i) throws IOException {
delegate.writeInt(i);
}
private void write(Directory directory) throws IOException {
long nextGeneration = getNextPendingGeneration();
String segmentFileName =
IndexFileNames.fileNameFromGeneration(IndexFileNames.PENDING_SEGMENTS, "", nextGeneration);
// Always advance the generation on write:
generation = nextGeneration;
IndexOutput segnOutput = null;
boolean success = false;
try {
segnOutput = directory.createOutput(segmentFileName, IOContext.DEFAULT);
CodecUtil.writeIndexHeader(
segnOutput,
"segments",
VERSION_CURRENT,
StringHelper.randomId(),
Long.toString(nextGeneration, Character.MAX_RADIX));
segnOutput.writeVInt(Version.LATEST.major);
segnOutput.writeVInt(Version.LATEST.minor);
segnOutput.writeVInt(Version.LATEST.bugfix);
segnOutput.writeLong(version);
segnOutput.writeInt(counter); // write counter
segnOutput.writeInt(size());
if (size() > 0) {
Version minSegmentVersion = null;
// We do a separate loop up front so we can write the minSegmentVersion before
// any SegmentInfo; this makes it cleaner to throw IndexFormatTooOldExc at read time:
for (SegmentCommitInfo siPerCommit : this) {
Version segmentVersion = siPerCommit.info.getVersion();
if (minSegmentVersion == null || segmentVersion.onOrAfter(minSegmentVersion) == false) {
minSegmentVersion = segmentVersion;
}
}
segnOutput.writeVInt(minSegmentVersion.major);
segnOutput.writeVInt(minSegmentVersion.minor);
segnOutput.writeVInt(minSegmentVersion.bugfix);
}
// write infos
for (SegmentCommitInfo siPerCommit : this) {
SegmentInfo si = siPerCommit.info;
segnOutput.writeString(si.name);
byte segmentID[] = si.getId();
// TODO: remove this in lucene 6, we don't need to include 4.x segments in commits anymore
if (segmentID == null) {
segnOutput.writeByte((byte) 0);
} else {
if (segmentID.length != StringHelper.ID_LENGTH) {
throw new IllegalStateException(
"cannot write segment: invalid id segment="
+ si.name
+ "id="
+ StringHelper.idToString(segmentID));
}
segnOutput.writeByte((byte) 1);
segnOutput.writeBytes(segmentID, segmentID.length);
}
segnOutput.writeString(si.getCodec().getName());
segnOutput.writeLong(siPerCommit.getDelGen());
int delCount = siPerCommit.getDelCount();
if (delCount < 0 || delCount > si.maxDoc()) {
throw new IllegalStateException(
"cannot write segment: invalid maxDoc segment="
+ si.name
+ " maxDoc="
+ si.maxDoc()
+ " delCount="
+ delCount);
}
segnOutput.writeInt(delCount);
segnOutput.writeLong(siPerCommit.getFieldInfosGen());
segnOutput.writeLong(siPerCommit.getDocValuesGen());
segnOutput.writeSetOfStrings(siPerCommit.getFieldInfosFiles());
final Map<Integer, Set<String>> dvUpdatesFiles = siPerCommit.getDocValuesUpdatesFiles();
segnOutput.writeInt(dvUpdatesFiles.size());
for (Entry<Integer, Set<String>> e : dvUpdatesFiles.entrySet()) {
segnOutput.writeInt(e.getKey());
segnOutput.writeSetOfStrings(e.getValue());
}
}
segnOutput.writeMapOfStrings(userData);
CodecUtil.writeFooter(segnOutput);
segnOutput.close();
directory.sync(Collections.singleton(segmentFileName));
success = true;
} finally {
if (success) {
pendingCommit = true;
} else {
// We hit an exception above; try to close the file
// but suppress any exception:
IOUtils.closeWhileHandlingException(segnOutput);
// Try not to leave a truncated segments_N file in
// the index:
IOUtils.deleteFilesIgnoringExceptions(directory, segmentFileName);
}
}
}
