private void ReadFields(IndexInput meta)
{
int fieldNumber = meta.ReadVInt();
while (fieldNumber != -1)
{
int fieldType = meta.ReadByte();
if (fieldType == NUMBER)
{
numerics[fieldNumber] = ReadNumericEntry(meta);
}
else if (fieldType == BYTES)
{
binaries[fieldNumber] = ReadBinaryEntry(meta);
}
else if (fieldType == SORTED)
{
sorteds[fieldNumber] = ReadSortedEntry(meta);
}
else if (fieldType == SORTED_SET)
{
sortedSets[fieldNumber] = ReadSortedSetEntry(meta);
}
else
{
throw new CorruptIndexException("invalid entry type: " + fieldType + ", input=" + meta);
}
fieldNumber = meta.ReadVInt();
}
}
public void Read(IndexInput input, FieldInfos fieldInfos)
{
this.term = null; // invalidate cache
int start = input.ReadVInt();
int length = input.ReadVInt();
int totalLength = start + length;
if (preUTF8Strings)
{
text.SetLength(totalLength);
input.ReadChars(text.result, start, length);
}
else
{
if (dirty)
{
// Fully convert all bytes since bytes is dirty
UnicodeUtil.UTF16toUTF8(text.result, 0, text.length, bytes);
bytes.SetLength(totalLength);
input.ReadBytes(bytes.result, start, length);
UnicodeUtil.UTF8toUTF16(bytes.result, 0, totalLength, text);
dirty = false;
}
else
{
// Incrementally convert only the UTF8 bytes that are new:
bytes.SetLength(totalLength);
input.ReadBytes(bytes.result, start, length);
UnicodeUtil.UTF8toUTF16(bytes.result, start, length, text);
}
}
this.field = fieldInfos.FieldName(input.ReadVInt());
}
public override void VisitDocument(int n, StoredFieldVisitor visitor)
{
SeekIndex(n);
FieldsStream.Seek(IndexStream.ReadLong());
int numFields = FieldsStream.ReadVInt();
for (int fieldIDX = 0; fieldIDX < numFields; fieldIDX++)
{
int fieldNumber = FieldsStream.ReadVInt();
FieldInfo fieldInfo = FieldInfos.FieldInfo(fieldNumber);
int bits = FieldsStream.ReadByte() & 0xFF;
Debug.Assert(bits <= (FIELD_IS_NUMERIC_MASK | FIELD_IS_BINARY), "bits=" + bits.ToString("x"));
switch (visitor.NeedsField(fieldInfo))
{
case StoredFieldVisitor.Status.YES:
ReadField(visitor, fieldInfo, bits);
break;
case StoredFieldVisitor.Status.NO:
SkipField(bits);
break;
case StoredFieldVisitor.Status.STOP:
return;
}
}
}
/// <summary>
/// Increments the enumeration to the next element. True if one exists. </summary>
public bool Next()
{
PrevBuffer.Set(TermBuffer);
//System.out.println(" ste setPrev=" + prev() + " this=" + this);
if (Position++ >= Size - 1)
{
TermBuffer.Reset();
//System.out.println(" EOF");
return(false);
}
TermBuffer.Read(Input, FieldInfos);
NewSuffixStart = TermBuffer.NewSuffixStart;
TermInfo_Renamed.DocFreq = Input.ReadVInt(); // read doc freq
TermInfo_Renamed.FreqPointer += Input.ReadVLong(); // read freq pointer
TermInfo_Renamed.ProxPointer += Input.ReadVLong(); // read prox pointer
if (TermInfo_Renamed.DocFreq >= SkipInterval)
{
TermInfo_Renamed.SkipOffset = Input.ReadVInt();
}
if (IsIndex)
{
IndexPointer += Input.ReadVLong(); // read index pointer
}
//System.out.println(" ste ret term=" + term());
return(true);
}
public void Read(IndexInput input, FieldInfos fieldInfos)
{
this.Term = null; // invalidate cache
NewSuffixStart = input.ReadVInt();
int length = input.ReadVInt();
int totalLength = NewSuffixStart + length;
Debug.Assert(totalLength <= ByteBlockPool.BYTE_BLOCK_SIZE - 2, "termLength=" + totalLength + ",resource=" + input);
if (Bytes.Bytes.Length < totalLength)
{
Bytes.Grow(totalLength);
}
Bytes.Length = totalLength;
input.ReadBytes(Bytes.Bytes, NewSuffixStart, length);
int fieldNumber = input.ReadVInt();
if (fieldNumber != CurrentFieldNumber)
{
CurrentFieldNumber = fieldNumber;
// NOTE: too much sneakiness here, seriously this is a negative vint?!
if (CurrentFieldNumber == -1)
{
Field = "";
}
else
{
Debug.Assert(fieldInfos.FieldInfo(CurrentFieldNumber) != null, CurrentFieldNumber.ToString());
Field = String.Intern(fieldInfos.FieldInfo(CurrentFieldNumber).Name);
}
}
else
{
Debug.Assert(Field.Equals(fieldInfos.FieldInfo(fieldNumber).Name), "currentFieldNumber=" + CurrentFieldNumber + " field=" + Field + " vs " + fieldInfos.FieldInfo(fieldNumber) == null ? "null" : fieldInfos.FieldInfo(fieldNumber).Name);
}
}
protected internal override int ReadSkipData(int level, IndexInput skipStream)
{
int delta;
if (currentFieldStoresPayloads)
{
// the current field stores payloads.
// if the doc delta is odd then we have
// to read the current payload length
// because it differs from the length of the
// previous payload
delta = skipStream.ReadVInt();
if ((delta & 1) != 0)
{
payloadLength[level] = skipStream.ReadVInt();
}
delta = Number.URShift(delta, 1);
}
else
{
delta = skipStream.ReadVInt();
}
freqPointer[level] += skipStream.ReadVInt();
proxPointer[level] += skipStream.ReadVInt();
return(delta);
}
public VariableGapTermsIndexReader(Directory dir, FieldInfos fieldInfos, String segment, int indexDivisor,
String segmentSuffix, IOContext context)
{
_input =
dir.OpenInput(
IndexFileNames.SegmentFileName(segment, segmentSuffix,
VariableGapTermsIndexWriter.TERMS_INDEX_EXTENSION), new IOContext(context, true));
var success = false;
Debug.Assert(indexDivisor == -1 || indexDivisor > 0);
try
{
_version = ReadHeader(_input);
_indexDivisor = indexDivisor;
if (_version >= VariableGapTermsIndexWriter.VERSION_CHECKSUM)
CodecUtil.ChecksumEntireFile(_input);
SeekDir(_input, _dirOffset);
// Read directory
var numFields = _input.ReadVInt();
if (numFields < 0)
{
throw new CorruptIndexException("invalid numFields: " + numFields + " (resource=" + _input + ")");
}
for (var i = 0; i < numFields; i++)
{
var field = _input.ReadVInt();
var indexStart = _input.ReadVLong();
var fieldInfo = fieldInfos.FieldInfo(field);
try
{
_fields.Add(fieldInfo, new FieldIndexData(indexStart, this));
}
catch (ArgumentException)
{
throw new CorruptIndexException(String.Format("Duplicate Field: {0}, Resource: {1}",
fieldInfo.Name, _input));
}
}
success = true;
}
finally
{
if (indexDivisor > 0)
{
_input.Dispose();
_input = null;
if (success)
{
_indexLoaded = true;
}
}
}
}
protected internal override int ReadSkipData(int level, IndexInput skipStream)
{
int delta;
if (CurrentFieldStoresPayloads)
{
// the current field stores payloads.
// if the doc delta is odd then we have
// to read the current payload length
// because it differs from the length of the
// previous payload
delta = skipStream.ReadVInt();
if ((delta & 1) != 0)
{
PayloadLength_Renamed[level] = skipStream.ReadVInt();
}
delta = (int)((uint)delta >> 1);
}
else
{
delta = skipStream.ReadVInt();
}
FreqPointer_Renamed[level] += skipStream.ReadVInt();
ProxPointer_Renamed[level] += skipStream.ReadVInt();
return(delta);
}
public void Read(IndexInput input, FieldInfos fieldInfos)
{
this.Term = null; // invalidate cache
NewSuffixStart = input.ReadVInt();
int length = input.ReadVInt();
int totalLength = NewSuffixStart + length;
Debug.Assert(totalLength <= ByteBlockPool.BYTE_BLOCK_SIZE - 2, "termLength=" + totalLength + ",resource=" + input);
if (Bytes.Bytes.Length < totalLength)
{
Bytes.Grow(totalLength);
}
Bytes.Length = totalLength;
input.ReadBytes(Bytes.Bytes, NewSuffixStart, length);
int fieldNumber = input.ReadVInt();
if (fieldNumber != CurrentFieldNumber)
{
CurrentFieldNumber = fieldNumber;
// NOTE: too much sneakiness here, seriously this is a negative vint?!
if (CurrentFieldNumber == -1)
{
Field = "";
}
else
{
Debug.Assert(fieldInfos.FieldInfo(CurrentFieldNumber) != null, CurrentFieldNumber.ToString());
Field = String.Intern(fieldInfos.FieldInfo(CurrentFieldNumber).Name);
}
}
else
{
Debug.Assert(Field.Equals(fieldInfos.FieldInfo(fieldNumber).Name), "currentFieldNumber=" + CurrentFieldNumber + " field=" + Field + " vs " + fieldInfos.FieldInfo(fieldNumber) == null ? "null" : fieldInfos.FieldInfo(fieldNumber).Name);
}
}
private void ReadFields(IndexInput meta, FieldInfos infos)
{
int fieldNumber = meta.ReadVInt();
while (fieldNumber != -1)
{
// check should be: infos.fieldInfo(fieldNumber) != null, which incorporates negative check
// but docvalues updates are currently buggy here (loading extra stuff, etc): LUCENE-5616
if (fieldNumber < 0)
{
// trickier to validate more: because we re-use for norms, because we use multiple entries
// for "composite" types like sortedset, etc.
throw new Exception("Invalid field number: " + fieldNumber + " (resource=" + meta + ")");
}
byte type = meta.ReadByte();
if (type == Lucene45DocValuesFormat.NUMERIC)
{
Numerics[fieldNumber] = ReadNumericEntry(meta);
}
else if (type == Lucene45DocValuesFormat.BINARY)
{
BinaryEntry b = ReadBinaryEntry(meta);
Binaries[fieldNumber] = b;
}
else if (type == Lucene45DocValuesFormat.SORTED)
{
ReadSortedField(fieldNumber, meta, infos);
}
else if (type == Lucene45DocValuesFormat.SORTED_SET)
{
SortedSetEntry ss = ReadSortedSetEntry(meta);
SortedSets[fieldNumber] = ss;
if (ss.Format == Lucene45DocValuesConsumer.SORTED_SET_WITH_ADDRESSES)
{
ReadSortedSetFieldWithAddresses(fieldNumber, meta, infos);
}
else if (ss.Format == Lucene45DocValuesConsumer.SORTED_SET_SINGLE_VALUED_SORTED)
{
if (meta.ReadVInt() != fieldNumber)
{
throw new Exception("sortedset entry for field: " + fieldNumber + " is corrupt (resource=" + meta + ")");
}
if (meta.ReadByte() != Lucene45DocValuesFormat.SORTED)
{
throw new Exception("sortedset entry for field: " + fieldNumber + " is corrupt (resource=" + meta + ")");
}
ReadSortedField(fieldNumber, meta, infos);
}
else
{
throw new Exception();
}
}
else
{
throw new Exception("invalid type: " + type + ", resource=" + meta);
}
fieldNumber = meta.ReadVInt();
}
}
private void ReadSortedField(int fieldNumber, IndexInput meta, FieldInfos infos)
{
// sorted = binary + numeric
if (meta.ReadVInt() != fieldNumber)
{
throw new Exception("sorted entry for field: " + fieldNumber + " is corrupt (resource=" + meta + ")");
}
if (meta.ReadByte() != Lucene45DocValuesFormat.BINARY)
{
throw new Exception("sorted entry for field: " + fieldNumber + " is corrupt (resource=" + meta + ")");
}
BinaryEntry b = ReadBinaryEntry(meta);
Binaries[fieldNumber] = b;
if (meta.ReadVInt() != fieldNumber)
{
throw new Exception("sorted entry for field: " + fieldNumber + " is corrupt (resource=" + meta + ")");
}
if (meta.ReadByte() != Lucene45DocValuesFormat.NUMERIC)
{
throw new Exception("sorted entry for field: " + fieldNumber + " is corrupt (resource=" + meta + ")");
}
NumericEntry n = ReadNumericEntry(meta);
Ords[fieldNumber] = n;
}
/// <summary>
/// Sole constructor. </summary>
public CompressingTermVectorsReader(Directory d, SegmentInfo si, string segmentSuffix, FieldInfos fn, IOContext context, string formatName, CompressionMode compressionMode)
{
this.compressionMode = compressionMode;
string segment = si.Name;
bool success = false;
fieldInfos = fn;
numDocs = si.DocCount;
ChecksumIndexInput indexStream = null;
try
{
// Load the index into memory
string indexStreamFN = IndexFileNames.SegmentFileName(segment, segmentSuffix, CompressingTermVectorsWriter.VECTORS_INDEX_EXTENSION);
indexStream = d.OpenChecksumInput(indexStreamFN, context);
string codecNameIdx = formatName + CompressingTermVectorsWriter.CODEC_SFX_IDX;
version = CodecUtil.CheckHeader(indexStream, codecNameIdx, CompressingTermVectorsWriter.VERSION_START, CompressingTermVectorsWriter.VERSION_CURRENT);
Debug.Assert(CodecUtil.HeaderLength(codecNameIdx) == indexStream.FilePointer);
indexReader = new CompressingStoredFieldsIndexReader(indexStream, si);
if (version >= CompressingTermVectorsWriter.VERSION_CHECKSUM)
{
indexStream.ReadVLong(); // the end of the data file
CodecUtil.CheckFooter(indexStream);
}
else
{
CodecUtil.CheckEOF(indexStream);
}
indexStream.Dispose();
indexStream = null;
// Open the data file and read metadata
string vectorsStreamFN = IndexFileNames.SegmentFileName(segment, segmentSuffix, CompressingTermVectorsWriter.VECTORS_EXTENSION);
vectorsStream = d.OpenInput(vectorsStreamFN, context);
string codecNameDat = formatName + CompressingTermVectorsWriter.CODEC_SFX_DAT;
int version2 = CodecUtil.CheckHeader(vectorsStream, codecNameDat, CompressingTermVectorsWriter.VERSION_START, CompressingTermVectorsWriter.VERSION_CURRENT);
if (version != version2)
{
throw new Exception("Version mismatch between stored fields index and data: " + version + " != " + version2);
}
Debug.Assert(CodecUtil.HeaderLength(codecNameDat) == vectorsStream.FilePointer);
packedIntsVersion = vectorsStream.ReadVInt();
chunkSize = vectorsStream.ReadVInt();
decompressor = compressionMode.NewDecompressor();
this.reader = new BlockPackedReaderIterator(vectorsStream, packedIntsVersion, CompressingTermVectorsWriter.BLOCK_SIZE, 0);
success = true;
}
finally
{
if (!success)
{
IOUtils.CloseWhileHandlingException(this, indexStream);
}
}
}
public int ReadBlock()
{
buffer[0] = input.ReadVInt();
int count = buffer[0] <= 3 ? baseBlockSize - 1 : 2 * baseBlockSize - 1;
Debug.Assert(buffer.Length >= count, "buffer.length=" + buffer.Length + " count=" + count);
for (int i = 0; i < count; i++)
{
buffer[i + 1] = input.ReadVInt();
}
return(1 + count);
}
public FSTTermsReader(SegmentReadState state, PostingsReaderBase postingsReader)
{
string termsFileName = IndexFileNames.SegmentFileName(state.SegmentInfo.Name, state.SegmentSuffix, FSTTermsWriter.TERMS_EXTENSION);
this.postingsReader = postingsReader;
IndexInput @in = state.Directory.OpenInput(termsFileName, state.Context);
bool success = false;
try
{
version = ReadHeader(@in);
if (version >= FSTTermsWriter.TERMS_VERSION_CHECKSUM)
{
CodecUtil.ChecksumEntireFile(@in);
}
this.postingsReader.Init(@in);
SeekDir(@in);
FieldInfos fieldInfos = state.FieldInfos;
int numFields = @in.ReadVInt();
for (int i = 0; i < numFields; i++)
{
int fieldNumber = @in.ReadVInt();
FieldInfo fieldInfo = fieldInfos.FieldInfo(fieldNumber);
long numTerms = @in.ReadVLong();
long sumTotalTermFreq = fieldInfo.FieldIndexOptions == IndexOptions.DOCS_ONLY ? -1 : @in.ReadVLong();
long sumDocFreq = @in.ReadVLong();
int docCount = @in.ReadVInt();
int longsSize = @in.ReadVInt();
TermsReader current = new TermsReader(this, fieldInfo, @in, numTerms, sumTotalTermFreq, sumDocFreq, docCount, longsSize);
TermsReader previous;
// LUCENENET NOTE: This simulates a put operation in Java,
// getting the prior value first before setting it.
fields.TryGetValue(fieldInfo.Name, out previous);
fields[fieldInfo.Name] = current;
CheckFieldSummary(state.SegmentInfo, @in, current, previous);
}
success = true;
}
finally
{
if (success)
{
IOUtils.Close(@in);
}
else
{
IOUtils.CloseWhileHandlingException(@in);
}
}
}
public /*internal*/ Document.Document Doc(int n, FieldSelector fieldSelector)
{
SeekIndex(n);
long position = indexStream.ReadLong();
fieldsStream.Seek(position);
var doc = new Document.Document();
int numFields = fieldsStream.ReadVInt();
for (int i = 0; i < numFields; i++)
{
int fieldNumber = fieldsStream.ReadVInt();
FieldInfo fi = fieldInfos.FieldInfo(fieldNumber);
FieldSelectorResult acceptField = fieldSelector == null?FieldSelectorResult.LOAD:fieldSelector.Accept(fi.name);
byte bits = fieldsStream.ReadByte();
System.Diagnostics.Debug.Assert(bits <= FieldsWriter.FIELD_IS_COMPRESSED + FieldsWriter.FIELD_IS_TOKENIZED + FieldsWriter.FIELD_IS_BINARY);
bool compressed = (bits & FieldsWriter.FIELD_IS_COMPRESSED) != 0;
System.Diagnostics.Debug.Assert(
(!compressed || (format < FieldsWriter.FORMAT_LUCENE_3_0_NO_COMPRESSED_FIELDS)),
"compressed fields are only allowed in indexes of version <= 2.9");
bool tokenize = (bits & FieldsWriter.FIELD_IS_TOKENIZED) != 0;
bool binary = (bits & FieldsWriter.FIELD_IS_BINARY) != 0;
//TODO: Find an alternative approach here if this list continues to grow beyond the
//list of 5 or 6 currently here. See Lucene 762 for discussion
if (acceptField.Equals(FieldSelectorResult.LOAD))
{
AddField(doc, fi, binary, compressed, tokenize);
}
else if (acceptField.Equals(FieldSelectorResult.LOAD_AND_BREAK))
{
AddField(doc, fi, binary, compressed, tokenize);
break; //Get out of this loop
}
else if (acceptField.Equals(FieldSelectorResult.LAZY_LOAD))
{
AddFieldLazy(doc, fi, binary, compressed, tokenize);
}
else if (acceptField.Equals(FieldSelectorResult.SIZE))
{
SkipField(binary, compressed, AddFieldSize(doc, fi, binary, compressed));
}
else if (acceptField.Equals(FieldSelectorResult.SIZE_AND_BREAK))
{
AddFieldSize(doc, fi, binary, compressed);
break;
}
else
{
SkipField(binary, compressed);
}
}
return(doc);
}
public override int NextDoc()
{
if (++docIt >= upto)
{
return(DocIdSetIterator.NO_MORE_DOCS);
}
postingInput.Seek(offsets[docIt]);
currFreq = postingInput.ReadVInt();
// reset variables used in nextPosition
pos = 0;
endOffset = 0;
return(docs[docIt]);
}
private void Read(IndexInput input, String fileName)
{
int firstInt = input.ReadVInt();
if (firstInt < 0)
{
// This is a real format
format = firstInt;
}
else
{
format = FORMAT_PRE;
}
if (format != FORMAT_PRE & format != FORMAT_START)
{
throw new CorruptIndexException("unrecognized format " + format + " in file \"" + fileName + "\"");
}
int size;
if (format == FORMAT_PRE)
{
size = firstInt;
}
else
{
size = input.ReadVInt(); //read in the size
}
for (int i = 0; i < size; i++)
{
String name = StringHelper.Intern(input.ReadString());
byte bits = input.ReadByte();
bool isIndexed = (bits & IS_INDEXED) != 0;
bool storeTermVector = (bits & STORE_TERMVECTOR) != 0;
bool storePositionsWithTermVector = (bits & STORE_POSITIONS_WITH_TERMVECTOR) != 0;
bool storeOffsetWithTermVector = (bits & STORE_OFFSET_WITH_TERMVECTOR) != 0;
bool omitNorms = (bits & OMIT_NORMS) != 0;
bool storePayloads = (bits & STORE_PAYLOADS) != 0;
bool omitTermFreqAndPositions = (bits & OMIT_TERM_FREQ_AND_POSITIONS) != 0;
AddInternal(name, isIndexed, storeTermVector, storePositionsWithTermVector, storeOffsetWithTermVector, omitNorms, storePayloads, omitTermFreqAndPositions);
}
if (input.FilePointer != input.Length())
{
throw new CorruptIndexException("did not read all bytes from file \"" + fileName + "\": read " + input.FilePointer + " vs size " + input.Length());
}
}
internal static BinaryEntry ReadBinaryEntry(IndexInput meta)
{
BinaryEntry entry = new BinaryEntry();
entry.Format = meta.ReadVInt();
entry.MissingOffset = meta.ReadLong();
entry.MinLength = meta.ReadVInt();
entry.MaxLength = meta.ReadVInt();
entry.Count = meta.ReadVLong();
entry.Offset = meta.ReadLong();
switch (entry.Format)
{
case Lucene45DocValuesConsumer.BINARY_FIXED_UNCOMPRESSED:
break;
case Lucene45DocValuesConsumer.BINARY_PREFIX_COMPRESSED:
entry.AddressInterval = meta.ReadVInt();
entry.AddressesOffset = meta.ReadLong();
entry.PackedIntsVersion = meta.ReadVInt();
entry.BlockSize = meta.ReadVInt();
break;
case Lucene45DocValuesConsumer.BINARY_VARIABLE_UNCOMPRESSED:
entry.AddressesOffset = meta.ReadLong();
entry.PackedIntsVersion = meta.ReadVInt();
entry.BlockSize = meta.ReadVInt();
break;
default:
throw new Exception("Unknown format: " + entry.Format + ", input=" + meta);
}
return(entry);
}
private BytesRef DoNext()
{
if (++currentOrd >= OuterInstance.NumValues)
{
return(null);
}
else
{
int start = Input.ReadVInt();
int suffix = Input.ReadVInt();
Input.ReadBytes(termBuffer.Bytes, start, suffix);
termBuffer.Length = start + suffix;
return(termBuffer);
}
}
public override int NextPosition()
{
if (LazyProxPointer != -1)
{
ProxIn.Seek(LazyProxPointer);
LazyProxPointer = -1;
}
// scan over any docs that were iterated without their positions
if (PosPendingCount > Freq_Renamed)
{
Position = 0;
while (PosPendingCount != Freq_Renamed)
{
if ((ProxIn.ReadByte() & 0x80) == 0)
{
PosPendingCount--;
}
}
}
Position += ProxIn.ReadVInt();
PosPendingCount--;
Debug.Assert(PosPendingCount >= 0, "nextPosition() was called too many times (more than freq() times) posPendingCount=" + PosPendingCount);
return(Position);
}
public void ReadBlock()
{
for (int i = 0; i < buffer.Length; i++)
{
buffer[i] = @in.ReadVInt();
}
}
protected internal override int NextUnreadDoc()
{
int docAcc = Accum;
int frq = 1;
IndexInput freqIn = this.FreqIn;
bool omitTF = IndexOmitsTF;
int loopLimit = Limit;
Bits liveDocs = this.LiveDocs;
for (int i = Ord; i < loopLimit; i++)
{
int code = freqIn.ReadVInt();
if (omitTF)
{
docAcc += code;
}
else
{
docAcc += (int)((uint)code >> 1); // shift off low bit
frq = ReadFreq(freqIn, code);
}
if (liveDocs.Get(docAcc))
{
Freq_Renamed = frq;
Ord = i + 1;
return(Accum = docAcc);
}
}
Ord = Limit;
Freq_Renamed = frq;
Accum = docAcc;
return(NO_MORE_DOCS);
}
public override FieldsProducer FieldsProducer(SegmentReadState readState)
{
// Load our ID:
string idFileName = IndexFileNames.SegmentFileName(readState.SegmentInfo.Name, readState.SegmentSuffix, ID_EXTENSION);
IndexInput @in = readState.Directory.OpenInput(idFileName, readState.Context);
bool success = false;
int id;
try
{
CodecUtil.CheckHeader(@in, RAM_ONLY_NAME, VERSION_START, VERSION_LATEST);
id = @in.ReadVInt();
success = true;
}
finally
{
if (!success)
{
IOUtils.CloseWhileHandlingException(@in);
}
else
{
IOUtils.Close(@in);
}
}
lock (State)
{
return(State[id]);
}
}
protected override int ReadSkipData(int level, IndexInput skipStream)
{
int delta;
Debug.Assert(_indexOptions == FieldInfo.IndexOptions.DOCS_AND_FREQS_AND_POSITIONS ||
!_currentFieldStoresPayloads);
if (_currentFieldStoresPayloads)
{
// the current field stores payloads.
// if the doc delta is odd then we have
// to read the current payload length
// because it differs from the length of the
// previous payload
delta = skipStream.ReadVInt();
if ((delta & 1) != 0)
{
_payloadLength[level] = skipStream.ReadVInt();
}
delta = (int)((uint)delta >> 1);
}
else
{
delta = skipStream.ReadVInt();
}
if (_indexOptions != FieldInfo.IndexOptions.DOCS_ONLY)
{
_freqIndex[level].Read(skipStream, false);
}
_docIndex[level].Read(skipStream, false);
if (_indexOptions != FieldInfo.IndexOptions.DOCS_AND_FREQS_AND_POSITIONS)
{
return(delta);
}
_posIndex[level].Read(skipStream, false);
if (_currentFieldStoresPayloads)
{
_payloadPointer[level] += skipStream.ReadVInt();
}
return(delta);
}
public override void Init(IndexInput termsIn)
{
_version = CodecUtil.CheckHeader(termsIn, PulsingPostingsWriter.CODEC,
PulsingPostingsWriter.VERSION_START,
PulsingPostingsWriter.VERSION_CURRENT);
_maxPositions = termsIn.ReadVInt();
_wrappedPostingsReader.Init(termsIn);
if (_wrappedPostingsReader is PulsingPostingsReader || _version < PulsingPostingsWriter.VERSION_META_ARRAY)
{
_fields = null;
}
else
{
_fields = new SortedDictionary <int, int>();
var summaryFileName = IndexFileNames.SegmentFileName(_segmentState.SegmentInfo.Name,
_segmentState.SegmentSuffix, PulsingPostingsWriter.SUMMARY_EXTENSION);
IndexInput input = null;
try
{
input =
_segmentState.Directory.OpenInput(summaryFileName, _segmentState.Context);
CodecUtil.CheckHeader(input,
PulsingPostingsWriter.CODEC,
_version,
PulsingPostingsWriter.VERSION_CURRENT);
var numField = input.ReadVInt();
for (var i = 0; i < numField; i++)
{
var fieldNum = input.ReadVInt();
var longsSize = input.ReadVInt();
_fields.Add(fieldNum, longsSize);
}
}
finally
{
IOUtils.CloseWhileHandlingException(input);
}
}
}
public TermsReader(FieldInfos fieldInfos, IndexInput @in, int termCount)
{
this.termCount = termCount;
int fieldNumber = @in.ReadVInt();
field = fieldInfos.FieldInfo(fieldNumber);
if (field.FieldIndexOptions != IndexOptions.DOCS_ONLY)
{
sumTotalTermFreq = @in.ReadVLong();
}
else
{
sumTotalTermFreq = -1;
}
sumDocFreq = @in.ReadVLong();
docCount = @in.ReadVInt();
fst = new FST <BytesRef>(@in, outputs);
}
private int ReadDeltaPosition()
{
int delta = proxStream.ReadVInt();
if (currentFieldStoresPayloads)
{
// if the current field stores payloads then
// the position delta is shifted one bit to the left.
// if the LSB is set, then we have to read the current
// payload length
if ((delta & 1) != 0)
{
payloadLength = proxStream.ReadVInt();
}
delta = Number.URShift(delta, 1);
needToLoadPayload = true;
}
return(delta);
}
public bool MoveNext()
{
if (input.FilePointer < input.Length())
{
int code = input.ReadVInt();
if ((code & 1) != 0)
{
field = input.ReadString();
}
int prefix = Number.URShift(code, 1);
int suffix = input.ReadVInt();
bytes.Grow(prefix + suffix);
input.ReadBytes(bytes.Bytes, prefix, suffix);
bytes.Length = prefix + suffix;
term.Set(field, bytes);
return(true);
}
return(false);
}
internal static NumericEntry ReadNumericEntry(IndexInput meta)
{
NumericEntry entry = new NumericEntry();
entry.Format = meta.ReadVInt();
entry.MissingOffset = meta.ReadLong();
entry.PackedIntsVersion = meta.ReadVInt();
entry.Offset = meta.ReadLong();
entry.Count = meta.ReadVLong();
entry.BlockSize = meta.ReadVInt();
switch (entry.Format)
{
case Lucene45DocValuesConsumer.GCD_COMPRESSED:
entry.MinValue = meta.ReadLong();
entry.Gcd = meta.ReadLong();
break;
case Lucene45DocValuesConsumer.TABLE_COMPRESSED:
if (entry.Count > int.MaxValue)
{
throw new Exception("Cannot use TABLE_COMPRESSED with more than MAX_VALUE values, input=" + meta);
}
int uniqueValues = meta.ReadVInt();
if (uniqueValues > 256)
{
throw new Exception("TABLE_COMPRESSED cannot have more than 256 distinct values, input=" + meta);
}
entry.Table = new long[uniqueValues];
for (int i = 0; i < uniqueValues; ++i)
{
entry.Table[i] = meta.ReadLong();
}
break;
case Lucene45DocValuesConsumer.DELTA_COMPRESSED:
break;
default:
throw new Exception("Unknown format: " + entry.Format + ", input=" + meta);
}
return(entry);
}
/// <summary>Increments the enumeration to the next element. True if one exists.</summary>
public override bool Next()
{
if (position++ >= size - 1)
{
prevBuffer.Set(termBuffer);
termBuffer.Reset();
return(false);
}
prevBuffer.Set(termBuffer);
termBuffer.Read(input, fieldInfos);
termInfo.docFreq = input.ReadVInt(); // read doc freq
termInfo.freqPointer += input.ReadVLong(); // read freq pointer
termInfo.proxPointer += input.ReadVLong(); // read prox pointer
if (format == -1)
{
// just read skipOffset in order to increment file pointer;
// value is never used since skipTo is switched off
if (!isIndex)
{
if (termInfo.docFreq > formatM1SkipInterval)
{
termInfo.skipOffset = input.ReadVInt();
}
}
}
else
{
if (termInfo.docFreq >= skipInterval)
{
termInfo.skipOffset = input.ReadVInt();
}
}
if (isIndex)
{
indexPointer += input.ReadVLong(); // read index pointer
}
return(true);
}
internal int ReadFreq(IndexInput freqIn, int code)
{
if ((code & 1) != 0) // if low bit is set
{
return(1); // freq is one
}
else
{
return(freqIn.ReadVInt()); // else read freq
}
}
public CompoundFileReader(Directory dir, System.String name, int readBufferSize)
{
directory = dir;
fileName = name;
this.readBufferSize = readBufferSize;
bool success = false;
try
{
stream = dir.OpenInput(name, readBufferSize);
// read the directory and init files
int count = stream.ReadVInt();
FileEntry entry = null;
for (int i = 0; i < count; i++)
{
long offset = stream.ReadLong();
System.String id = stream.ReadString();
if (entry != null)
{
// set length of the previous entry
entry.length = offset - entry.offset;
}
entry = new FileEntry {
offset = offset
};
entries[id] = entry;
}
// set the length of the final entry
if (entry != null)
{
entry.length = stream.Length() - entry.offset;
}
success = true;
}
finally
{
if (!success && (stream != null))
{
try
{
stream.Close();
}
catch (System.IO.IOException)
{
}
}
}
}
public override void Init(IndexInput termsIn)
{
_version = CodecUtil.CheckHeader(termsIn, PulsingPostingsWriter.CODEC,
PulsingPostingsWriter.VERSION_START,
PulsingPostingsWriter.VERSION_CURRENT);
_maxPositions = termsIn.ReadVInt();
_wrappedPostingsReader.Init(termsIn);
if (_wrappedPostingsReader is PulsingPostingsReader || _version < PulsingPostingsWriter.VERSION_META_ARRAY)
{
_fields = null;
}
else
{
_fields = new SortedDictionary<int, int>();
var summaryFileName = IndexFileNames.SegmentFileName(_segmentState.SegmentInfo.Name,
_segmentState.SegmentSuffix, PulsingPostingsWriter.SUMMARY_EXTENSION);
IndexInput input = null;
try
{
input =
_segmentState.Directory.OpenInput(summaryFileName, _segmentState.Context);
CodecUtil.CheckHeader(input,
PulsingPostingsWriter.CODEC,
_version,
PulsingPostingsWriter.VERSION_CURRENT);
var numField = input.ReadVInt();
for (var i = 0; i < numField; i++)
{
var fieldNum = input.ReadVInt();
var longsSize = input.ReadVInt();
_fields.Add(fieldNum, longsSize);
}
}
finally
{
IOUtils.CloseWhileHandlingException(input);
}
}
}
/// <summary>
/// Sole constructor. </summary>
public CompressingStoredFieldsReader(Directory d, SegmentInfo si, string segmentSuffix, FieldInfos fn, IOContext context, string formatName, CompressionMode compressionMode)
{
this.CompressionMode_Renamed = compressionMode;
string segment = si.Name;
bool success = false;
FieldInfos = fn;
NumDocs = si.DocCount;
ChecksumIndexInput indexStream = null;
try
{
string indexStreamFN = IndexFileNames.SegmentFileName(segment, segmentSuffix, Lucene40StoredFieldsWriter.FIELDS_INDEX_EXTENSION);
string fieldsStreamFN = IndexFileNames.SegmentFileName(segment, segmentSuffix, Lucene40StoredFieldsWriter.FIELDS_EXTENSION);
// Load the index into memory
indexStream = d.OpenChecksumInput(indexStreamFN, context);
string codecNameIdx = formatName + CompressingStoredFieldsWriter.CODEC_SFX_IDX;
Version_Renamed = CodecUtil.CheckHeader(indexStream, codecNameIdx, CompressingStoredFieldsWriter.VERSION_START, CompressingStoredFieldsWriter.VERSION_CURRENT);
Debug.Assert(CodecUtil.HeaderLength(codecNameIdx) == indexStream.FilePointer);
IndexReader = new CompressingStoredFieldsIndexReader(indexStream, si);
long maxPointer = -1;
if (Version_Renamed >= CompressingStoredFieldsWriter.VERSION_CHECKSUM)
{
maxPointer = indexStream.ReadVLong();
CodecUtil.CheckFooter(indexStream);
}
else
{
CodecUtil.CheckEOF(indexStream);
}
indexStream.Dispose();
indexStream = null;
// Open the data file and read metadata
FieldsStream = d.OpenInput(fieldsStreamFN, context);
if (Version_Renamed >= CompressingStoredFieldsWriter.VERSION_CHECKSUM)
{
if (maxPointer + CodecUtil.FooterLength() != FieldsStream.Length())
{
throw new CorruptIndexException("Invalid fieldsStream maxPointer (file truncated?): maxPointer=" + maxPointer + ", length=" + FieldsStream.Length());
}
}
else
{
maxPointer = FieldsStream.Length();
}
this.MaxPointer = maxPointer;
string codecNameDat = formatName + CompressingStoredFieldsWriter.CODEC_SFX_DAT;
int fieldsVersion = CodecUtil.CheckHeader(FieldsStream, codecNameDat, CompressingStoredFieldsWriter.VERSION_START, CompressingStoredFieldsWriter.VERSION_CURRENT);
if (Version_Renamed != fieldsVersion)
{
throw new CorruptIndexException("Version mismatch between stored fields index and data: " + Version_Renamed + " != " + fieldsVersion);
}
Debug.Assert(CodecUtil.HeaderLength(codecNameDat) == FieldsStream.FilePointer);
if (Version_Renamed >= CompressingStoredFieldsWriter.VERSION_BIG_CHUNKS)
{
ChunkSize_Renamed = FieldsStream.ReadVInt();
}
else
{
ChunkSize_Renamed = -1;
}
PackedIntsVersion = FieldsStream.ReadVInt();
Decompressor = compressionMode.NewDecompressor();
this.Bytes = new BytesRef();
success = true;
}
finally
{
if (!success)
{
IOUtils.CloseWhileHandlingException(this, indexStream);
}
}
}
public FixedGapTermsIndexReader(Directory dir, FieldInfos fieldInfos, String segment, int indexDivisor,
IComparer<BytesRef> termComp, String segmentSuffix, IOContext context)
{
_termComp = termComp;
Debug.Assert(indexDivisor == -1 || indexDivisor > 0);
_input =
dir.OpenInput(
IndexFileNames.SegmentFileName(segment, segmentSuffix,
FixedGapTermsIndexWriter.TERMS_INDEX_EXTENSION),
context);
var success = false;
try
{
_version = ReadHeader(_input);
if (_version >= FixedGapTermsIndexWriter.VERSION_CHECKSUM)
CodecUtil.ChecksumEntireFile(_input);
indexInterval = _input.ReadInt();
if (indexInterval < 1)
{
throw new CorruptIndexException(String.Format("Invalid indexInterval: {0}, Resource: {1}",
indexInterval, _input));
}
_indexDivisor = indexDivisor;
if (indexDivisor < 0)
{
_totalIndexInterval = indexInterval;
}
else
{
// In case terms index gets loaded, later, on demand
_totalIndexInterval = indexInterval*indexDivisor;
}
Debug.Assert(_totalIndexInterval > 0);
SeekDir(_input, _dirOffset);
// Read directory
int numFields = _input.ReadVInt();
if (numFields < 0)
throw new CorruptIndexException(String.Format("Invalid numFields: {0}, Resource: {1}", numFields,
_input));
for (int i = 0; i < numFields; i++)
{
int field = _input.ReadVInt();
int numIndexTerms = _input.ReadVInt();
if (numIndexTerms < 0)
throw new CorruptIndexException(String.Format("Invalid numIndexTerms: {0}, Resource: {1}",
numIndexTerms,
_input));
long termsStart = _input.ReadVLong();
long indexStart = _input.ReadVLong();
long packedIndexStart = _input.ReadVLong();
long packedOffsetsStart = _input.ReadVLong();
if (packedIndexStart < indexStart)
throw new CorruptIndexException(
String.Format(
"Invalid packedIndexStart: {0}, IndexStart: {1}, NumIndexTerms: {2}, Resource: {3}",
packedIndexStart,
indexStart, numIndexTerms, _input));
FieldInfo fieldInfo = fieldInfos.FieldInfo(field);
try
{
_fields.Add(fieldInfo,
new FieldIndexData(numIndexTerms, indexStart, termsStart, packedIndexStart,
packedOffsetsStart, this));
}
catch (ArgumentException)
{
throw new CorruptIndexException(String.Format("Duplicate field: {0}, Resource {1}",
fieldInfo.Name,
_input));
}
}
success = true;
}
finally
{
if (!success)
{
IOUtils.CloseWhileHandlingException(_input);
}
if (indexDivisor > 0)
{
_input.Dispose();
_input = null;
if (success)
_indexLoaded = true;
_termBytesReader = _termBytes.Freeze(true);
}
}
}
public TermsReader(FieldInfos fieldInfos, IndexInput @in, int termCount)
{
this.termCount = termCount;
int fieldNumber = @in.ReadVInt();
field = fieldInfos.FieldInfo(fieldNumber);
if (field.FieldIndexOptions != IndexOptions.DOCS_ONLY)
{
sumTotalTermFreq = @in.ReadVLong();
}
else
{
sumTotalTermFreq = -1;
}
sumDocFreq = @in.ReadVLong();
docCount = @in.ReadVInt();
fst = new FST<BytesRef>(@in, outputs);
}
/// <summary>
/// Sole constructor. </summary>
public BlockTreeTermsReader(Directory dir, FieldInfos fieldInfos, SegmentInfo info, PostingsReaderBase postingsReader, IOContext ioContext, string segmentSuffix, int indexDivisor)
{
if (!InstanceFieldsInitialized)
{
InitializeInstanceFields();
InstanceFieldsInitialized = true;
}
this.PostingsReader = postingsReader;
this.Segment = info.Name;
@in = dir.OpenInput(IndexFileNames.SegmentFileName(Segment, segmentSuffix, BlockTreeTermsWriter.TERMS_EXTENSION), ioContext);
bool success = false;
IndexInput indexIn = null;
try
{
Version = ReadHeader(@in);
if (indexDivisor != -1)
{
indexIn = dir.OpenInput(IndexFileNames.SegmentFileName(Segment, segmentSuffix, BlockTreeTermsWriter.TERMS_INDEX_EXTENSION), ioContext);
int indexVersion = ReadIndexHeader(indexIn);
if (indexVersion != Version)
{
throw new CorruptIndexException("mixmatched version files: " + @in + "=" + Version + "," + indexIn + "=" + indexVersion);
}
}
// verify
if (indexIn != null && Version >= BlockTreeTermsWriter.VERSION_CHECKSUM)
{
CodecUtil.ChecksumEntireFile(indexIn);
}
// Have PostingsReader init itself
postingsReader.Init(@in);
// Read per-field details
SeekDir(@in, DirOffset);
if (indexDivisor != -1)
{
SeekDir(indexIn, IndexDirOffset);
}
int numFields = @in.ReadVInt();
if (numFields < 0)
{
throw new CorruptIndexException("invalid numFields: " + numFields + " (resource=" + @in + ")");
}
for (int i = 0; i < numFields; i++)
{
int field = @in.ReadVInt();
long numTerms = @in.ReadVLong();
Debug.Assert(numTerms >= 0);
int numBytes = @in.ReadVInt();
BytesRef rootCode = new BytesRef(new byte[numBytes]);
@in.ReadBytes(rootCode.Bytes, 0, numBytes);
rootCode.Length = numBytes;
FieldInfo fieldInfo = fieldInfos.FieldInfo(field);
Debug.Assert(fieldInfo != null, "field=" + field);
long sumTotalTermFreq = fieldInfo.FieldIndexOptions == FieldInfo.IndexOptions.DOCS_ONLY ? -1 : @in.ReadVLong();
long sumDocFreq = @in.ReadVLong();
int docCount = @in.ReadVInt();
int longsSize = Version >= BlockTreeTermsWriter.VERSION_META_ARRAY ? @in.ReadVInt() : 0;
if (docCount < 0 || docCount > info.DocCount) // #docs with field must be <= #docs
{
throw new CorruptIndexException("invalid docCount: " + docCount + " maxDoc: " + info.DocCount + " (resource=" + @in + ")");
}
if (sumDocFreq < docCount) // #postings must be >= #docs with field
{
throw new CorruptIndexException("invalid sumDocFreq: " + sumDocFreq + " docCount: " + docCount + " (resource=" + @in + ")");
}
if (sumTotalTermFreq != -1 && sumTotalTermFreq < sumDocFreq) // #positions must be >= #postings
{
throw new CorruptIndexException("invalid sumTotalTermFreq: " + sumTotalTermFreq + " sumDocFreq: " + sumDocFreq + " (resource=" + @in + ")");
}
long indexStartFP = indexDivisor != -1 ? indexIn.ReadVLong() : 0;
if (Fields.ContainsKey(fieldInfo.Name))
{
throw new CorruptIndexException("duplicate field: " + fieldInfo.Name + " (resource=" + @in + ")");
}
else
{
Fields[fieldInfo.Name] = new FieldReader(this, fieldInfo, numTerms, rootCode, sumTotalTermFreq, sumDocFreq, docCount, indexStartFP, longsSize, indexIn);
}
}
if (indexDivisor != -1)
{
indexIn.Dispose();
}
success = true;
}
finally
{
if (!success)
{
// this.close() will close in:
IOUtils.CloseWhileHandlingException(indexIn, this);
}
}
}
protected override int ReadSkipData(int level, IndexInput skipStream)
{
int delta;
Debug.Assert(_indexOptions == FieldInfo.IndexOptions.DOCS_AND_FREQS_AND_POSITIONS ||
!_currentFieldStoresPayloads);
if (_currentFieldStoresPayloads)
{
// the current field stores payloads.
// if the doc delta is odd then we have
// to read the current payload length
// because it differs from the length of the
// previous payload
delta = skipStream.ReadVInt();
if ((delta & 1) != 0)
{
_payloadLength[level] = skipStream.ReadVInt();
}
delta = (int) ((uint) delta >> 1);
}
else
{
delta = skipStream.ReadVInt();
}
if (_indexOptions != FieldInfo.IndexOptions.DOCS_ONLY)
_freqIndex[level].Read(skipStream, false);
_docIndex[level].Read(skipStream, false);
if (_indexOptions != FieldInfo.IndexOptions.DOCS_AND_FREQS_AND_POSITIONS) return delta;
_posIndex[level].Read(skipStream, false);
if (_currentFieldStoresPayloads)
_payloadPointer[level] += skipStream.ReadVInt();
return delta;
}
internal int ReadFreq(IndexInput freqIn, int code)
{
if ((code & 1) != 0) // if low bit is set
{
return 1; // freq is one
}
else
{
return freqIn.ReadVInt(); // else read freq
}
}
public BlockTermsReader(TermsIndexReaderBase indexReader, Directory dir, FieldInfos fieldInfos, SegmentInfo info,
PostingsReaderBase postingsReader, IOContext context,
String segmentSuffix)
{
_postingsReader = postingsReader;
_input =
dir.OpenInput(
IndexFileNames.SegmentFileName(info.Name, segmentSuffix, BlockTermsWriter.TERMS_EXTENSION),
context);
var success = false;
try
{
_version = ReadHeader(_input);
// Have PostingsReader init itself
postingsReader.Init(_input);
// Read per-field details
SeekDir(_input, _dirOffset);
int numFields = _input.ReadVInt();
if (numFields < 0)
{
throw new CorruptIndexException(String.Format("Invalid number of fields: {0}, Resource: {1}",
numFields, _input));
}
for (var i = 0; i < numFields; i++)
{
var field = _input.ReadVInt();
var numTerms = _input.ReadVLong();
Debug.Assert(numTerms >= 0);
var termsStartPointer = _input.ReadVLong();
var fieldInfo = fieldInfos.FieldInfo(field);
var sumTotalTermFreq = fieldInfo.FieldIndexOptions == FieldInfo.IndexOptions.DOCS_ONLY
? -1
: _input.ReadVLong();
var sumDocFreq = _input.ReadVLong();
var docCount = _input.ReadVInt();
var longsSize = _version >= BlockTermsWriter.VERSION_META_ARRAY ? _input.ReadVInt() : 0;
if (docCount < 0 || docCount > info.DocCount)
{
// #docs with field must be <= #docs
throw new CorruptIndexException(
String.Format("Invalid DocCount: {0}, MaxDoc: {1}, Resource: {2}", docCount, info.DocCount,
_input));
}
if (sumDocFreq < docCount)
{
// #postings must be >= #docs with field
throw new CorruptIndexException(
String.Format("Invalid sumDocFreq: {0}, DocCount: {1}, Resource: {2}", sumDocFreq, docCount,
_input));
}
if (sumTotalTermFreq != -1 && sumTotalTermFreq < sumDocFreq)
{
// #positions must be >= #postings
throw new CorruptIndexException(
String.Format("Invalid sumTotalTermFreq: {0}, sumDocFreq: {1}, Resource: {2}",
sumTotalTermFreq, sumDocFreq, _input));
}
try
{
_fields.Add(fieldInfo.Name,
new FieldReader(fieldInfo, this, numTerms, termsStartPointer, sumTotalTermFreq, sumDocFreq,
docCount,
longsSize));
}
catch (ArgumentException)
{
throw new CorruptIndexException(String.Format("Duplicate fields: {0}, Resource: {1}",
fieldInfo.Name, _input));
}
}
success = true;
}
finally
{
if (!success)
{
_input.Dispose();
}
}
_indexReader = indexReader;
}
