public BloomFilteredFieldsProducer(BloomFilteringPostingsFormat outerInstance, SegmentReadState state) { this.outerInstance = outerInstance; var bloomFileName = IndexFileNames.SegmentFileName( state.SegmentInfo.Name, state.SegmentSuffix, BLOOM_EXTENSION); ChecksumIndexInput bloomIn = null; var success = false; try { bloomIn = state.Directory.OpenChecksumInput(bloomFileName, state.Context); var version = CodecUtil.CheckHeader(bloomIn, /*BLOOM_CODEC_NAME*/ outerInstance.Name, VERSION_START, VERSION_CURRENT); // Load the hash function used in the BloomFilter // hashFunction = HashFunction.forName(bloomIn.readString()); // Load the delegate postings format var delegatePostingsFormat = ForName(bloomIn.ReadString()); _delegateFieldsProducer = delegatePostingsFormat .FieldsProducer(state); var numBlooms = bloomIn.ReadInt32(); for (var i = 0; i < numBlooms; i++) { var fieldNum = bloomIn.ReadInt32(); var bloom = FuzzySet.Deserialize(bloomIn); var fieldInfo = state.FieldInfos.FieldInfo(fieldNum); _bloomsByFieldName.Add(fieldInfo.Name, bloom); } if (version >= VERSION_CHECKSUM) { CodecUtil.CheckFooter(bloomIn); } else { #pragma warning disable 612, 618 CodecUtil.CheckEOF(bloomIn); #pragma warning restore 612, 618 } IOUtils.Dispose(bloomIn); success = true; } finally { if (!success) { IOUtils.DisposeWhileHandlingException(bloomIn, _delegateFieldsProducer); } } }
public override SegmentInfo Read(Directory dir, string segment, IOContext context) { string fileName = IndexFileNames.SegmentFileName(segment, "", Lucene46SegmentInfoFormat.SI_EXTENSION); ChecksumIndexInput input = dir.OpenChecksumInput(fileName, context); bool success = false; try { int codecVersion = CodecUtil.CheckHeader(input, Lucene46SegmentInfoFormat.CODEC_NAME, Lucene46SegmentInfoFormat.VERSION_START, Lucene46SegmentInfoFormat.VERSION_CURRENT); string version = input.ReadString(); int docCount = input.ReadInt32(); if (docCount < 0) { throw new CorruptIndexException("invalid docCount: " + docCount + " (resource=" + input + ")"); } bool isCompoundFile = input.ReadByte() == SegmentInfo.YES; IDictionary <string, string> diagnostics = input.ReadStringStringMap(); ISet <string> files = input.ReadStringSet(); if (codecVersion >= Lucene46SegmentInfoFormat.VERSION_CHECKSUM) { CodecUtil.CheckFooter(input); } else { #pragma warning disable 612, 618 CodecUtil.CheckEOF(input); #pragma warning restore 612, 618 } SegmentInfo si = new SegmentInfo(dir, version, segment, docCount, isCompoundFile, null, diagnostics); si.SetFiles(files); success = true; return(si); } finally { if (!success) { IOUtils.DisposeWhileHandlingException(input); } else { input.Dispose(); } } }
public override FieldInfos Read(Directory directory, string segmentName, string segmentSuffix, IOContext context) { string fileName = IndexFileNames.SegmentFileName(segmentName, segmentSuffix, Lucene46FieldInfosFormat.EXTENSION); ChecksumIndexInput input = directory.OpenChecksumInput(fileName, context); bool success = false; try { int codecVersion = CodecUtil.CheckHeader(input, Lucene46FieldInfosFormat.CODEC_NAME, Lucene46FieldInfosFormat.FORMAT_START, Lucene46FieldInfosFormat.FORMAT_CURRENT); int size = input.ReadVInt32(); //read in the size FieldInfo[] infos = new FieldInfo[size]; for (int i = 0; i < size; i++) { string name = input.ReadString(); int fieldNumber = input.ReadVInt32(); byte bits = input.ReadByte(); bool isIndexed = (bits & Lucene46FieldInfosFormat.IS_INDEXED) != 0; bool storeTermVector = (bits & Lucene46FieldInfosFormat.STORE_TERMVECTOR) != 0; bool omitNorms = (bits & Lucene46FieldInfosFormat.OMIT_NORMS) != 0; bool storePayloads = (bits & Lucene46FieldInfosFormat.STORE_PAYLOADS) != 0; IndexOptions indexOptions; if (!isIndexed) { indexOptions = IndexOptions.NONE; } else if ((bits & Lucene46FieldInfosFormat.OMIT_TERM_FREQ_AND_POSITIONS) != 0) { indexOptions = IndexOptions.DOCS_ONLY; } else if ((bits & Lucene46FieldInfosFormat.OMIT_POSITIONS) != 0) { indexOptions = IndexOptions.DOCS_AND_FREQS; } else if ((bits & Lucene46FieldInfosFormat.STORE_OFFSETS_IN_POSTINGS) != 0) { indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS_AND_OFFSETS; } else { indexOptions = IndexOptions.DOCS_AND_FREQS_AND_POSITIONS; } // DV Types are packed in one byte byte val = input.ReadByte(); DocValuesType docValuesType = GetDocValuesType(input, (byte)(val & 0x0F)); DocValuesType normsType = GetDocValuesType(input, (byte)((val.TripleShift(4)) & 0x0F)); long dvGen = input.ReadInt64(); IDictionary <string, string> attributes = input.ReadStringStringMap(); infos[i] = new FieldInfo(name, isIndexed, fieldNumber, storeTermVector, omitNorms, storePayloads, indexOptions, docValuesType, normsType, attributes.AsReadOnly()); infos[i].DocValuesGen = dvGen; } if (codecVersion >= Lucene46FieldInfosFormat.FORMAT_CHECKSUM) { CodecUtil.CheckFooter(input); } else { #pragma warning disable 612, 618 CodecUtil.CheckEOF(input); #pragma warning restore 612, 618 } FieldInfos fieldInfos = new FieldInfos(infos); success = true; return(fieldInfos); } finally { if (success) { input.Dispose(); } else { IOUtils.DisposeWhileHandlingException(input); } } }
/// <summary> Read a particular segmentFileName. Note that this may /// throw an IOException if a commit is in process. /// /// </summary> /// <param name="directory">-- directory containing the segments file /// </param> /// <param name="segmentFileName">-- segment file to load /// </param> /// <throws> CorruptIndexException if the index is corrupt </throws> /// <throws> IOException if there is a low-level IO error </throws> public void Read(Directory directory, System.String segmentFileName) { bool success = false; // Clear any previous segments: Clear(); var input = new ChecksumIndexInput(directory.OpenInput(segmentFileName)); generation = GenerationFromSegmentsFileName(segmentFileName); lastGeneration = generation; try { int format = input.ReadInt(); if (format < 0) { // file contains explicit format info // check that it is a format we can understand if (format < CURRENT_FORMAT) { throw new CorruptIndexException("Unknown format version: " + format); } version = input.ReadLong(); // read version counter = input.ReadInt(); // read counter } else { // file is in old format without explicit format info counter = format; } for (int i = input.ReadInt(); i > 0; i--) { // read segmentInfos Add(new SegmentInfo(directory, format, input)); } if (format >= 0) { // in old format the version number may be at the end of the file if (input.FilePointer >= input.Length()) { version = (DateTime.UtcNow.Ticks / TimeSpan.TicksPerMillisecond); } // old file format without version number else { version = input.ReadLong(); // read version } } if (format <= FORMAT_USER_DATA) { if (format <= FORMAT_DIAGNOSTICS) { userData = input.ReadStringStringMap(); } else if (0 != input.ReadByte()) { // TODO: Should be read-only map userData = new HashMap <string, string> { { "userData", input.ReadString() } }; } else { // TODO: Should be empty read-only map userData = new HashMap <string, string>(); } } else { // TODO: Should be empty read-only map userData = new HashMap <string, string>(); } if (format <= FORMAT_CHECKSUM) { long checksumNow = input.Checksum; long checksumThen = input.ReadLong(); if (checksumNow != checksumThen) { throw new CorruptIndexException("checksum mismatch in segments file"); } } success = true; } finally { input.Close(); if (!success) { // Clear any segment infos we had loaded so we // have a clean slate on retry: Clear(); } } }