/// <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.GetFilePointer());
                indexReader = new CompressingStoredFieldsIndexReader(indexStream, si);

                if (version >= CompressingTermVectorsWriter.VERSION_CHECKSUM)
                {
                    indexStream.ReadVInt64(); // the end of the data file
                    CodecUtil.CheckFooter(indexStream);
                }
                else
                {
#pragma warning disable 612, 618
                    CodecUtil.CheckEOF(indexStream);
#pragma warning restore 612, 618
                }
                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.GetFilePointer());

                packedIntsVersion = vectorsStream.ReadVInt32();
                chunkSize         = vectorsStream.ReadVInt32();
                decompressor      = compressionMode.NewDecompressor();
                this.reader       = new BlockPackedReaderIterator(vectorsStream, packedIntsVersion, CompressingTermVectorsWriter.BLOCK_SIZE, 0);

                success = true;
            }
            finally
            {
                if (!success)
                {
                    IOUtils.DisposeWhileHandlingException(this, indexStream);
                }
            }
        }
Пример #2
0
        /// <summary>
        /// Sole constructor. </summary>
        public CompressingTermVectorsWriter(Directory directory, SegmentInfo si, string segmentSuffix, IOContext context, string formatName, CompressionMode compressionMode, int chunkSize)
        {
            if (Debugging.AssertsEnabled)
            {
                Debugging.Assert(directory != null);
            }
            this.directory       = directory;
            this.segment         = si.Name;
            this.segmentSuffix   = segmentSuffix;
            this.compressionMode = compressionMode;
            this.compressor      = compressionMode.NewCompressor();
            this.chunkSize       = chunkSize;

            numDocs      = 0;
            pendingDocs  = new LinkedList <DocData>();
            termSuffixes = new GrowableByteArrayDataOutput(ArrayUtil.Oversize(chunkSize, 1));
            payloadBytes = new GrowableByteArrayDataOutput(ArrayUtil.Oversize(1, 1));
            lastTerm     = new BytesRef(ArrayUtil.Oversize(30, 1));

            bool        success     = false;
            IndexOutput indexStream = directory.CreateOutput(IndexFileNames.SegmentFileName(segment, segmentSuffix, VECTORS_INDEX_EXTENSION), context);

            try
            {
                vectorsStream = directory.CreateOutput(IndexFileNames.SegmentFileName(segment, segmentSuffix, VECTORS_EXTENSION), context);

                string codecNameIdx = formatName + CODEC_SFX_IDX;
                string codecNameDat = formatName + CODEC_SFX_DAT;
                CodecUtil.WriteHeader(indexStream, codecNameIdx, VERSION_CURRENT);
                CodecUtil.WriteHeader(vectorsStream, codecNameDat, VERSION_CURRENT);
                if (Debugging.AssertsEnabled)
                {
                    Debugging.Assert(CodecUtil.HeaderLength(codecNameDat) == vectorsStream.Position); // LUCENENET specific: Renamed from getFilePointer() to match FileStream
                    Debugging.Assert(CodecUtil.HeaderLength(codecNameIdx) == indexStream.Position);   // LUCENENET specific: Renamed from getFilePointer() to match FileStream
                }

                indexWriter = new CompressingStoredFieldsIndexWriter(indexStream);
                indexStream = null;

                vectorsStream.WriteVInt32(PackedInt32s.VERSION_CURRENT);
                vectorsStream.WriteVInt32(chunkSize);
                writer = new BlockPackedWriter(vectorsStream, BLOCK_SIZE);

                positionsBuf      = new int[1024];
                startOffsetsBuf   = new int[1024];
                lengthsBuf        = new int[1024];
                payloadLengthsBuf = new int[1024];

                success = true;
            }
            finally
            {
                if (!success)
                {
                    IOUtils.DisposeWhileHandlingException(indexStream);
                    Abort();
                }
            }
        }
Пример #3
0
        /// <summary>
        /// Sole constructor. </summary>
        public CompressingTermVectorsWriter(Directory directory, SegmentInfo si, string segmentSuffix, IOContext context, string formatName, CompressionMode compressionMode, int chunkSize)
        {
            Debug.Assert(directory != null);
            this.Directory       = directory;
            this.Segment         = si.Name;
            this.SegmentSuffix   = segmentSuffix;
            this.CompressionMode = compressionMode;
            this.Compressor      = compressionMode.NewCompressor();
            this.ChunkSize       = chunkSize;

            NumDocs      = 0;
            PendingDocs  = new LinkedList <DocData>();
            TermSuffixes = new GrowableByteArrayDataOutput(ArrayUtil.Oversize(chunkSize, 1));
            PayloadBytes = new GrowableByteArrayDataOutput(ArrayUtil.Oversize(1, 1));
            LastTerm     = new BytesRef(ArrayUtil.Oversize(30, 1));

            bool        success     = false;
            IndexOutput indexStream = directory.CreateOutput(IndexFileNames.SegmentFileName(Segment, segmentSuffix, VECTORS_INDEX_EXTENSION), context);

            try
            {
                VectorsStream = directory.CreateOutput(IndexFileNames.SegmentFileName(Segment, segmentSuffix, VECTORS_EXTENSION), context);

                string codecNameIdx = formatName + CODEC_SFX_IDX;
                string codecNameDat = formatName + CODEC_SFX_DAT;
                CodecUtil.WriteHeader(indexStream, codecNameIdx, VERSION_CURRENT);
                CodecUtil.WriteHeader(VectorsStream, codecNameDat, VERSION_CURRENT);
                Debug.Assert(CodecUtil.HeaderLength(codecNameDat) == VectorsStream.FilePointer);
                Debug.Assert(CodecUtil.HeaderLength(codecNameIdx) == indexStream.FilePointer);

                IndexWriter = new CompressingStoredFieldsIndexWriter(indexStream);
                indexStream = null;

                VectorsStream.WriteVInt(PackedInts.VERSION_CURRENT);
                VectorsStream.WriteVInt(chunkSize);
                Writer = new BlockPackedWriter(VectorsStream, BLOCK_SIZE);

                PositionsBuf      = new int[1024];
                StartOffsetsBuf   = new int[1024];
                LengthsBuf        = new int[1024];
                PayloadLengthsBuf = new int[1024];

                success = true;
            }
            finally
            {
                if (!success)
                {
                    IOUtils.CloseWhileHandlingException(indexStream);
                    Abort();
                }
            }
        }
Пример #4
0
        private int numBufferedDocs;   // docBase + numBufferedDocs == current doc ID

        /// <summary>
        /// Sole constructor. </summary>
        public CompressingStoredFieldsWriter(Directory directory, SegmentInfo si, string segmentSuffix, IOContext context, string formatName, CompressionMode compressionMode, int chunkSize)
        {
            if (Debugging.AssertsEnabled)
            {
                Debugging.Assert(directory != null);
            }
            this.directory       = directory;
            this.segment         = si.Name;
            this.segmentSuffix   = segmentSuffix;
            this.compressionMode = compressionMode;
            this.compressor      = compressionMode.NewCompressor();
            this.chunkSize       = chunkSize;
            this.docBase         = 0;
            this.bufferedDocs    = new GrowableByteArrayDataOutput(chunkSize);
            this.numStoredFields = new int[16];
            this.endOffsets      = new int[16];
            this.numBufferedDocs = 0;

            bool        success     = false;
            IndexOutput indexStream = directory.CreateOutput(IndexFileNames.SegmentFileName(segment, segmentSuffix, Lucene40StoredFieldsWriter.FIELDS_INDEX_EXTENSION), context);

            try
            {
                fieldsStream = directory.CreateOutput(IndexFileNames.SegmentFileName(segment, segmentSuffix, Lucene40StoredFieldsWriter.FIELDS_EXTENSION), context);

                string codecNameIdx = formatName + CODEC_SFX_IDX;
                string codecNameDat = formatName + CODEC_SFX_DAT;
                CodecUtil.WriteHeader(indexStream, codecNameIdx, VERSION_CURRENT);
                CodecUtil.WriteHeader(fieldsStream, codecNameDat, VERSION_CURRENT);
                if (Debugging.AssertsEnabled)
                {
                    Debugging.Assert(CodecUtil.HeaderLength(codecNameDat) == fieldsStream.Position); // LUCENENET specific: Renamed from getFilePointer() to match FileStream
                    Debugging.Assert(CodecUtil.HeaderLength(codecNameIdx) == indexStream.Position);  // LUCENENET specific: Renamed from getFilePointer() to match FileStream
                }

                indexWriter = new CompressingStoredFieldsIndexWriter(indexStream);
                indexStream = null;

                fieldsStream.WriteVInt32(chunkSize);
                fieldsStream.WriteVInt32(PackedInt32s.VERSION_CURRENT);

                success = true;
            }
            finally
            {
                if (!success)
                {
                    IOUtils.DisposeWhileHandlingException(indexStream);
                    Abort();
                }
            }
        }
        private int NumBufferedDocs;   // docBase + numBufferedDocs == current doc ID

        /// <summary>
        /// Sole constructor. </summary>
        public CompressingStoredFieldsWriter(Directory directory, SegmentInfo si, string segmentSuffix, IOContext context, string formatName, CompressionMode compressionMode, int chunkSize)
        {
            Debug.Assert(directory != null);
            this.Directory       = directory;
            this.Segment         = si.Name;
            this.SegmentSuffix   = segmentSuffix;
            this.CompressionMode = compressionMode;
            this.Compressor      = compressionMode.NewCompressor();
            this.ChunkSize       = chunkSize;
            this.DocBase         = 0;
            this.BufferedDocs    = new GrowableByteArrayDataOutput(chunkSize);
            this.NumStoredFields = new int[16];
            this.EndOffsets      = new int[16];
            this.NumBufferedDocs = 0;

            bool        success     = false;
            IndexOutput indexStream = directory.CreateOutput(IndexFileNames.SegmentFileName(Segment, segmentSuffix, Lucene40StoredFieldsWriter.FIELDS_INDEX_EXTENSION), context);

            try
            {
                FieldsStream = directory.CreateOutput(IndexFileNames.SegmentFileName(Segment, segmentSuffix, Lucene40StoredFieldsWriter.FIELDS_EXTENSION), context);

                string codecNameIdx = formatName + CODEC_SFX_IDX;
                string codecNameDat = formatName + CODEC_SFX_DAT;
                CodecUtil.WriteHeader(indexStream, codecNameIdx, VERSION_CURRENT);
                CodecUtil.WriteHeader(FieldsStream, codecNameDat, VERSION_CURRENT);
                Debug.Assert(CodecUtil.HeaderLength(codecNameDat) == FieldsStream.FilePointer);
                Debug.Assert(CodecUtil.HeaderLength(codecNameIdx) == indexStream.FilePointer);

                IndexWriter = new CompressingStoredFieldsIndexWriter(indexStream);
                indexStream = null;

                FieldsStream.WriteVInt(chunkSize);
                FieldsStream.WriteVInt(PackedInts.VERSION_CURRENT);

                success = true;
            }
            finally
            {
                if (!success)
                {
                    IOUtils.CloseWhileHandlingException(indexStream);
                    Abort();
                }
            }
        }
Пример #6
0
        /// <summary>
        /// Sole constructor. </summary>
        public CompressingStoredFieldsReader(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
            {
                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 = CodecUtil.CheckHeader(indexStream, codecNameIdx, CompressingStoredFieldsWriter.VERSION_START, CompressingStoredFieldsWriter.VERSION_CURRENT);
                if (Debugging.AssertsEnabled)
                {
                    Debugging.Assert(CodecUtil.HeaderLength(codecNameIdx) == indexStream.Position);                           // LUCENENET specific: Renamed from getFilePointer() to match FileStream
                }
                indexReader = new CompressingStoredFieldsIndexReader(indexStream, si);

                long maxPointer = -1;

                if (version >= CompressingStoredFieldsWriter.VERSION_CHECKSUM)
                {
                    maxPointer = indexStream.ReadVInt64();
                    CodecUtil.CheckFooter(indexStream);
                }
                else
                {
#pragma warning disable 612, 618
                    CodecUtil.CheckEOF(indexStream);
#pragma warning restore 612, 618
                }
                indexStream.Dispose();
                indexStream = null;

                // Open the data file and read metadata
                fieldsStream = d.OpenInput(fieldsStreamFN, context);
                if (version >= 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 != fieldsVersion)
                {
                    throw new CorruptIndexException("Version mismatch between stored fields index and data: " + version + " != " + fieldsVersion);
                }
                if (Debugging.AssertsEnabled)
                {
                    Debugging.Assert(CodecUtil.HeaderLength(codecNameDat) == fieldsStream.Position);                           // LUCENENET specific: Renamed from getFilePointer() to match FileStream
                }
                if (version >= CompressingStoredFieldsWriter.VERSION_BIG_CHUNKS)
                {
                    chunkSize = fieldsStream.ReadVInt32();
                }
                else
                {
                    chunkSize = -1;
                }
                packedIntsVersion = fieldsStream.ReadVInt32();
                decompressor      = compressionMode.NewDecompressor();
                this.bytes        = new BytesRef();

                success = true;
            }
            finally
            {
                if (!success)
                {
                    IOUtils.DisposeWhileHandlingException(this, indexStream);
                }
            }
        }
        /// <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);
                }
            }
        }