public BloomFilteredFieldsProducer(SegmentReadState state) throws IOException {
String bloomFileName =
IndexFileNames.segmentFileName(
state.segmentInfo.name, state.segmentSuffix, BLOOM_EXTENSION);
IndexInput bloomIn = null;
boolean success = false;
try {
bloomIn = state.directory.openInput(bloomFileName, state.context);
CodecUtil.checkHeader(bloomIn, BLOOM_CODEC_NAME, BLOOM_CODEC_VERSION, BLOOM_CODEC_VERSION);
// // Load the hash function used in the BloomFilter
// hashFunction = HashFunction.forName(bloomIn.readString());
// Load the delegate postings format
PostingsFormat delegatePostingsFormat = PostingsFormat.forName(bloomIn.readString());
this.delegateFieldsProducer = delegatePostingsFormat.fieldsProducer(state);
int numBlooms = bloomIn.readInt();
for (int i = 0; i < numBlooms; i++) {
int fieldNum = bloomIn.readInt();
FuzzySet bloom = FuzzySet.deserialize(bloomIn);
FieldInfo fieldInfo = state.fieldInfos.fieldInfo(fieldNum);
bloomsByFieldName.put(fieldInfo.name, bloom);
}
IOUtils.close(bloomIn);
success = true;
} finally {
if (!success) {
IOUtils.closeWhileHandlingException(bloomIn, delegateFieldsProducer);
}
}
}
private void verifyData(CoherenceDirectory dir, String fileName) throws IOException {
byte[] test = new byte[] {1, 2, 3, 4, 5, 6, 7, 8};
assertTrue(dir.fileExists(fileName));
assertEquals(38, dir.fileLength(fileName));
IndexInput indexInput = dir.openInput(fileName);
indexInput.readBytes(test, 0, 5);
assertEquals(8, test[0]);
assertEquals(-1, indexInput.readInt());
assertEquals(10, indexInput.readLong());
assertEquals(0, indexInput.readInt());
assertEquals(0, indexInput.readInt());
indexInput.readBytes(test, 0, 8);
assertEquals((byte) 1, test[0]);
assertEquals((byte) 8, test[7]);
indexInput.readBytes(test, 0, 5);
assertEquals((byte) 1, test[0]);
assertEquals((byte) 5, test[4]);
indexInput.seek(28);
assertEquals((byte) 4, indexInput.readByte());
indexInput.seek(30);
assertEquals((byte) 6, indexInput.readByte());
indexInput.close();
}
private void readFields(IndexInput meta, FieldInfos infos) throws IOException {
for (int fieldNumber = meta.readInt(); fieldNumber != -1; fieldNumber = meta.readInt()) {
FieldInfo info = infos.fieldInfo(fieldNumber);
if (info == null) {
throw new CorruptIndexException("Invalid field number: " + fieldNumber, meta);
} else if (!info.hasNorms()) {
throw new CorruptIndexException("Invalid field: " + info.name, meta);
}
NormsEntry entry = new NormsEntry();
entry.docsWithFieldOffset = meta.readLong();
entry.numDocsWithField = meta.readInt();
entry.bytesPerNorm = meta.readByte();
switch (entry.bytesPerNorm) {
case 0:
case 1:
case 2:
case 4:
case 8:
break;
default:
throw new CorruptIndexException(
"Invalid bytesPerValue: " + entry.bytesPerNorm + ", field: " + info.name, meta);
}
entry.normsOffset = meta.readLong();
norms.put(info.number, entry);
}
}
@Override
public void init(IndexInput termsIn) throws IOException {
// Make sure we are talking to the matching past writer
CodecUtil.checkHeader(
termsIn,
SepPostingsWriter.CODEC,
SepPostingsWriter.VERSION_START,
SepPostingsWriter.VERSION_START);
skipInterval = termsIn.readInt();
maxSkipLevels = termsIn.readInt();
skipMinimum = termsIn.readInt();
}
/**
* Creates an array with content retrieved from the given IndexInput.
*
* @param in an IndexInput, positioned at the start of Packed64-content.
* @param valueCount the number of elements.
* @param bitsPerValue the number of bits available for any given value.
* @throws java.io.IOException if the values for the backing array could not be retrieved.
*/
public Packed32(IndexInput in, int valueCount, int bitsPerValue) throws IOException {
super(valueCount, bitsPerValue);
int size = size(bitsPerValue, valueCount);
blocks = new int[size + 1]; // +1 due to non-conditional tricks
// TODO: find a faster way to bulk-read ints...
for (int i = 0; i < size; i++) {
blocks[i] = in.readInt();
}
if (size % 2 == 1) {
in.readInt(); // Align to long
}
updateCached();
}
static Map<String, String> readChecksums(Directory[] dirs, Map<String, String> defaultValue)
throws IOException {
long lastFound = -1;
Directory lastDir = null;
for (Directory dir : dirs) {
for (String name : dir.listAll()) {
if (!isChecksum(name)) {
continue;
}
long current = Long.parseLong(name.substring(CHECKSUMS_PREFIX.length()));
if (current > lastFound) {
lastFound = current;
lastDir = dir;
}
}
}
if (lastFound == -1) {
return defaultValue;
}
IndexInput indexInput = lastDir.openInput(CHECKSUMS_PREFIX + lastFound, IOContext.READONCE);
try {
indexInput.readInt(); // version
return indexInput.readStringStringMap();
} catch (Exception e) {
// failed to load checksums, ignore and return an empty map
return defaultValue;
} finally {
indexInput.close();
}
}
public static void IndexInputTest() throws Exception {
String path = "D:\\Lucene Document";
directory = FSDirectory.getDirectory(path);
IndexInput indexInput = directory.openInput("segments.gen");
int version = indexInput.readInt();
System.out.println(version);
System.out.println(indexInput.readString());
}
private void verifyData(ByteBufferDirectory dir) throws IOException {
byte[] test = new byte[] {1, 2, 3, 4, 5, 6, 7, 8};
assertThat(dir.fileExists("value1"), equalTo(true));
assertThat(dir.fileLength("value1"), equalTo(38l));
IndexInput indexInput = dir.openInput("value1", IOContext.DEFAULT);
indexInput.readBytes(test, 0, 5);
assertThat(test[0], equalTo((byte) 8));
assertThat(indexInput.readInt(), equalTo(-1));
assertThat(indexInput.readLong(), equalTo((long) 10));
assertThat(indexInput.readInt(), equalTo(0));
assertThat(indexInput.readInt(), equalTo(0));
indexInput.readBytes(test, 0, 8);
assertThat(test[0], equalTo((byte) 1));
assertThat(test[7], equalTo((byte) 8));
indexInput.readBytes(test, 0, 5);
assertThat(test[0], equalTo((byte) 1));
assertThat(test[4], equalTo((byte) 5));
indexInput.seek(28);
assertThat(indexInput.readByte(), equalTo((byte) 4));
indexInput.seek(30);
assertThat(indexInput.readByte(), equalTo((byte) 6));
indexInput.seek(0);
indexInput.readBytes(test, 0, 5);
assertThat(test[0], equalTo((byte) 8));
indexInput.close();
indexInput = dir.openInput("value1", IOContext.DEFAULT);
// iterate over all the data
for (int i = 0; i < 38; i++) {
indexInput.readByte();
}
indexInput.close();
}
@Override
public int readInt() throws IOException {
return delegate.readInt();
}
public Object run(IndexCommit commit) throws CorruptIndexException, IOException {
if (commit != null) {
if (directory != commit.getDirectory())
throw new IOException("the specified commit does not match the specified Directory");
return doBody(commit.getSegmentsFileName());
}
String segmentFileName = null;
long lastGen = -1;
long gen = 0;
int genLookaheadCount = 0;
IOException exc = null;
int retryCount = 0;
boolean useFirstMethod = true;
// Loop until we succeed in calling doBody() without
// hitting an IOException. An IOException most likely
// means a commit was in process and has finished, in
// the time it took us to load the now-old infos files
// (and segments files). It's also possible it's a
// true error (corrupt index). To distinguish these,
// on each retry we must see "forward progress" on
// which generation we are trying to load. If we
// don't, then the original error is real and we throw
// it.
// We have three methods for determining the current
// generation. We try the first two in parallel (when
// useFirstMethod is true), and fall back to the third
// when necessary.
while (true) {
if (useFirstMethod) {
// List the directory and use the highest
// segments_N file. This method works well as long
// as there is no stale caching on the directory
// contents (NOTE: NFS clients often have such stale
// caching):
String[] files = null;
long genA = -1;
files = directory.listAll();
if (files != null) {
genA = getCurrentSegmentGeneration(files);
}
if (infoStream != null) {
message("directory listing genA=" + genA);
}
// Also open segments.gen and read its
// contents. Then we take the larger of the two
// gens. This way, if either approach is hitting
// a stale cache (NFS) we have a better chance of
// getting the right generation.
long genB = -1;
for (int i = 0; i < defaultGenFileRetryCount; i++) {
IndexInput genInput = null;
try {
genInput = directory.openInput(IndexFileNames.SEGMENTS_GEN);
} catch (FileNotFoundException e) {
if (infoStream != null) {
message("segments.gen open: FileNotFoundException " + e);
}
break;
} catch (IOException e) {
if (infoStream != null) {
message("segments.gen open: IOException " + e);
}
}
if (genInput != null) {
try {
int version = genInput.readInt();
if (version == FORMAT_LOCKLESS) {
long gen0 = genInput.readLong();
long gen1 = genInput.readLong();
if (infoStream != null) {
message("fallback check: " + gen0 + "; " + gen1);
}
if (gen0 == gen1) {
// The file is consistent.
genB = gen0;
break;
}
}
} catch (IOException err2) {
// will retry
} finally {
genInput.close();
}
}
try {
Thread.sleep(defaultGenFileRetryPauseMsec);
} catch (InterruptedException ie) {
throw new ThreadInterruptedException(ie);
}
}
if (infoStream != null) {
message(IndexFileNames.SEGMENTS_GEN + " check: genB=" + genB);
}
// Pick the larger of the two gen's:
if (genA > genB) gen = genA;
else gen = genB;
if (gen == -1) {
// Neither approach found a generation
throw new IndexNotFoundException(
"no segments* file found in " + directory + ": files: " + Arrays.toString(files));
}
}
if (useFirstMethod && lastGen == gen && retryCount >= 2) {
// Give up on first method -- this is 3rd cycle on
// listing directory and checking gen file to
// attempt to locate the segments file.
useFirstMethod = false;
}
// Second method: since both directory cache and
// file contents cache seem to be stale, just
// advance the generation.
if (!useFirstMethod) {
if (genLookaheadCount < defaultGenLookaheadCount) {
gen++;
genLookaheadCount++;
if (infoStream != null) {
message("look ahead increment gen to " + gen);
}
} else {
// All attempts have failed -- throw first exc:
throw exc;
}
} else if (lastGen == gen) {
// This means we're about to try the same
// segments_N last tried.
retryCount++;
} else {
// Segment file has advanced since our last loop
// (we made "progress"), so reset retryCount:
retryCount = 0;
}
lastGen = gen;
segmentFileName = IndexFileNames.fileNameFromGeneration(IndexFileNames.SEGMENTS, "", gen);
try {
Object v = doBody(segmentFileName);
if (infoStream != null) {
message("success on " + segmentFileName);
}
return v;
} catch (IOException err) {
// Save the original root cause:
if (exc == null) {
exc = err;
}
if (infoStream != null) {
message(
"primary Exception on '"
+ segmentFileName
+ "': "
+ err
+ "'; will retry: retryCount="
+ retryCount
+ "; gen = "
+ gen);
}
if (gen > 1 && useFirstMethod && retryCount == 1) {
// This is our second time trying this same segments
// file (because retryCount is 1), and, there is
// possibly a segments_(N-1) (because gen > 1).
// So, check if the segments_(N-1) exists and
// try it if so:
String prevSegmentFileName =
IndexFileNames.fileNameFromGeneration(IndexFileNames.SEGMENTS, "", gen - 1);
final boolean prevExists;
prevExists = directory.fileExists(prevSegmentFileName);
if (prevExists) {
if (infoStream != null) {
message("fallback to prior segment file '" + prevSegmentFileName + "'");
}
try {
Object v = doBody(prevSegmentFileName);
if (infoStream != null) {
message("success on fallback " + prevSegmentFileName);
}
return v;
} catch (IOException err2) {
if (infoStream != null) {
message(
"secondary Exception on '"
+ prevSegmentFileName
+ "': "
+ err2
+ "'; will retry");
}
}
}
}
}
}
}
