Пример #1
0
        /// <summary>read as a d-gaps list </summary>
        private void  ReadDgaps(IndexInput input)
        {
            size  = input.ReadInt();            // (re)read size
            count = input.ReadInt();            // read count
            bits  = new byte[(size >> 3) + 1];  // allocate bits
            int last = 0;
            int n    = Count();

            while (n > 0)
            {
                last      += input.ReadVInt();
                bits[last] = input.ReadByte();
                n         -= BYTE_COUNTS[bits[last] & 0xFF];
            }
        }
Пример #2
0
        private int CheckValidFormat(IndexInput in_Renamed)
        {
            int format = in_Renamed.ReadInt();

            if (format > FORMAT_CURRENT)
            {
                throw new CorruptIndexException("Incompatible format version: " + format + " expected " + FORMAT_CURRENT + " or less");
            }
            return(format);
        }
Пример #3
0
        /// <summary>Constructs a bit vector from the file <code>name</code> in Directory
        /// <code>d</code>, as written by the {@link #write} method.
        /// </summary>
        public BitVector(Directory d, System.String name)
        {
            IndexInput input = d.OpenInput(name);

            try
            {
                size = input.ReadInt();                 // read size
                if (size == -1)
                {
                    ReadDgaps(input);
                }
                else
                {
                    ReadBits(input);
                }
            }
            finally
            {
                input.Close();
            }
        }
Пример #4
0
        internal SegmentTermEnum(IndexInput i, FieldInfos fis, bool isi)
        {
            input         = i;
            fieldInfos    = fis;
            isIndex       = isi;
            maxSkipLevels = 1;             // use single-level skip lists for formats > -3

            int firstInt = input.ReadInt();

            if (firstInt >= 0)
            {
                // original-format file, without explicit format version number
                format = 0;
                size   = firstInt;

                // back-compatible settings
                indexInterval = 128;
                skipInterval  = System.Int32.MaxValue;                // switch off skipTo optimization
            }
            else
            {
                // we have a format version number
                format = firstInt;

                // check that it is a format we can understand
                if (format < TermInfosWriter.FORMAT_CURRENT)
                {
                    throw new CorruptIndexException("Unknown format version:" + format + " expected " + TermInfosWriter.FORMAT_CURRENT + " or higher");
                }

                size = input.ReadLong();                 // read the size

                if (format == -1)
                {
                    if (!isIndex)
                    {
                        indexInterval        = input.ReadInt();
                        formatM1SkipInterval = input.ReadInt();
                    }
                    // switch off skipTo optimization for file format prior to 1.4rc2 in order to avoid a bug in
                    // skipTo implementation of these versions
                    skipInterval = System.Int32.MaxValue;
                }
                else
                {
                    indexInterval = input.ReadInt();
                    skipInterval  = input.ReadInt();
                    if (format <= TermInfosWriter.FORMAT)
                    {
                        // this new format introduces multi-level skipping
                        maxSkipLevels = input.ReadInt();
                    }
                }
                System.Diagnostics.Debug.Assert(indexInterval > 0, "indexInterval=" + indexInterval + " is negative; must be > 0");
                System.Diagnostics.Debug.Assert(skipInterval > 0, "skipInterval=" + skipInterval + " is negative; must be > 0");
            }
            if (format > TermInfosWriter.FORMAT_VERSION_UTF8_LENGTH_IN_BYTES)
            {
                termBuffer.SetPreUTF8Strings();
                scanBuffer.SetPreUTF8Strings();
                prevBuffer.SetPreUTF8Strings();
            }
        }
Пример #5
0
		/// <summary> Construct a new SegmentInfo instance by reading a
		/// previously saved SegmentInfo from input.
		/// 
		/// </summary>
		/// <param name="dir">directory to load from
		/// </param>
		/// <param name="format">format of the segments info file
		/// </param>
		/// <param name="input">input handle to read segment info from
		/// </param>
		internal SegmentInfo(Directory dir, int format, IndexInput input)
		{
			this.dir = dir;
			name = input.ReadString();
			docCount = input.ReadInt();
			if (format <= SegmentInfos.FORMAT_LOCKLESS)
			{
				delGen = input.ReadLong();
				if (format <= SegmentInfos.FORMAT_SHARED_DOC_STORE)
				{
					docStoreOffset = input.ReadInt();
					if (docStoreOffset != - 1)
					{
						docStoreSegment = input.ReadString();
						docStoreIsCompoundFile = (1 == input.ReadByte());
					}
					else
					{
						docStoreSegment = name;
						docStoreIsCompoundFile = false;
					}
				}
				else
				{
					docStoreOffset = - 1;
					docStoreSegment = name;
					docStoreIsCompoundFile = false;
				}
				if (format <= SegmentInfos.FORMAT_SINGLE_NORM_FILE)
				{
					hasSingleNormFile = (1 == input.ReadByte());
				}
				else
				{
					hasSingleNormFile = false;
				}
				int numNormGen = input.ReadInt();
				if (numNormGen == NO)
				{
					normGen = null;
				}
				else
				{
					normGen = new long[numNormGen];
					for (int j = 0; j < numNormGen; j++)
					{
						normGen[j] = input.ReadLong();
					}
				}
				isCompoundFile = (sbyte) input.ReadByte();
				preLockless = (isCompoundFile == CHECK_DIR);
				if (format <= SegmentInfos.FORMAT_DEL_COUNT)
				{
					delCount = input.ReadInt();
					System.Diagnostics.Debug.Assert(delCount <= docCount);
				}
				else
					delCount = - 1;
				if (format <= SegmentInfos.FORMAT_HAS_PROX)
					hasProx = input.ReadByte() == 1;
				else
					hasProx = true;
				
				if (format <= SegmentInfos.FORMAT_DIAGNOSTICS)
				{
					diagnostics = input.ReadStringStringMap();
				}
				else
				{
					diagnostics = new System.Collections.Generic.Dictionary<string,string>();
				}
			}
			else
			{
				delGen = CHECK_DIR;
				normGen = null;
				isCompoundFile = (sbyte) (CHECK_DIR);
				preLockless = true;
				hasSingleNormFile = false;
				docStoreOffset = - 1;
				docStoreIsCompoundFile = false;
				docStoreSegment = null;
				delCount = - 1;
				hasProx = true;
				diagnostics = new System.Collections.Generic.Dictionary<string,string>();
			}
		}
Пример #6
0
 /// <summary>Read as a bit set </summary>
 private void  ReadBits(IndexInput input)
 {
     count = input.ReadInt();             // read count
     bits  = new byte[(size >> 3) + 1];   // allocate bits
     input.ReadBytes(bits, 0, bits.Length);
 }
Пример #7
0
		internal FieldsReader(Directory d, System.String segment, FieldInfos fn, int readBufferSize, int docStoreOffset, int size)
		{
			bool success = false;
			isOriginal = true;
			try
			{
				fieldInfos = fn;
				
				cloneableFieldsStream = d.OpenInput(segment + "." + IndexFileNames.FIELDS_EXTENSION, readBufferSize);
				cloneableIndexStream = d.OpenInput(segment + "." + IndexFileNames.FIELDS_INDEX_EXTENSION, readBufferSize);
				
				// First version of fdx did not include a format
				// header, but, the first int will always be 0 in that
				// case
				int firstInt = cloneableIndexStream.ReadInt();
				if (firstInt == 0)
					format = 0;
				else
					format = firstInt;
				
				if (format > FieldsWriter.FORMAT_CURRENT
                    /* extra support for Lucene 3.0 indexes: */ && format != FieldsWriter.FORMAT_LUCENE_3_0_NO_COMPRESSED_FIELDS
                    )
					throw new CorruptIndexException("Incompatible format version: " + format + " expected " + FieldsWriter.FORMAT_CURRENT + " or lower");
				
				if (format > FieldsWriter.FORMAT)
					formatSize = 4;
				else
					formatSize = 0;
				
				if (format < FieldsWriter.FORMAT_VERSION_UTF8_LENGTH_IN_BYTES)
					cloneableFieldsStream.SetModifiedUTF8StringsMode();
				
				fieldsStream = (IndexInput) cloneableFieldsStream.Clone();
				
				long indexSize = cloneableIndexStream.Length() - formatSize;
				
				if (docStoreOffset != - 1)
				{
					// We read only a slice out of this shared fields file
					this.docStoreOffset = docStoreOffset;
					this.size = size;
					
					// Verify the file is long enough to hold all of our
					// docs
					System.Diagnostics.Debug.Assert(((int)(indexSize / 8)) >= size + this.docStoreOffset, "indexSize=" + indexSize + " size=" + size + " docStoreOffset=" + docStoreOffset);
				}
				else
				{
					this.docStoreOffset = 0;
					this.size = (int) (indexSize >> 3);
				}
				
				indexStream = (IndexInput) cloneableIndexStream.Clone();
				numTotalDocs = (int) (indexSize >> 3);
				success = true;
			}
			finally
			{
				// With lock-less commits, it's entirely possible (and
				// fine) to hit a FileNotFound exception above. In
				// this case, we want to explicitly close any subset
				// of things that were opened so that we don't have to
				// wait for a GC to do so.
				if (!success)
				{
					Close();
				}
			}
		}
Пример #8
0
		/// <summary>Read as a bit set </summary>
		private void  ReadBits(IndexInput input)
		{
			count = input.ReadInt(); // read count
			bits = new byte[(size >> 3) + 1]; // allocate bits
			input.ReadBytes(bits, 0, bits.Length);
		}
Пример #9
0
		/// <summary>read as a d-gaps list </summary>
		private void  ReadDgaps(IndexInput input)
		{
			size = input.ReadInt(); // (re)read size
			count = input.ReadInt(); // read count
			bits = new byte[(size >> 3) + 1]; // allocate bits
			int last = 0;
			int n = Count();
			while (n > 0)
			{
				last += input.ReadVInt();
				bits[last] = input.ReadByte();
				n -= BYTE_COUNTS[bits[last] & 0xFF];
			}
		}
Пример #10
0
        /// <summary> Construct a new SegmentInfo instance by reading a
        /// previously saved SegmentInfo from input.
        ///
        /// </summary>
        /// <param name="dir">directory to load from
        /// </param>
        /// <param name="format">format of the segments info file
        /// </param>
        /// <param name="input">input handle to read segment info from
        /// </param>
        internal SegmentInfo(Directory dir, int format, IndexInput input)
        {
            this.dir = dir;
            name     = input.ReadString();
            docCount = input.ReadInt();
            if (format <= SegmentInfos.FORMAT_LOCKLESS)
            {
                delGen = input.ReadLong();
                if (format <= SegmentInfos.FORMAT_SHARED_DOC_STORE)
                {
                    docStoreOffset = input.ReadInt();
                    if (docStoreOffset != -1)
                    {
                        docStoreSegment        = input.ReadString();
                        docStoreIsCompoundFile = (1 == input.ReadByte());
                    }
                    else
                    {
                        docStoreSegment        = name;
                        docStoreIsCompoundFile = false;
                    }
                }
                else
                {
                    docStoreOffset         = -1;
                    docStoreSegment        = name;
                    docStoreIsCompoundFile = false;
                }
                if (format <= SegmentInfos.FORMAT_SINGLE_NORM_FILE)
                {
                    hasSingleNormFile = (1 == input.ReadByte());
                }
                else
                {
                    hasSingleNormFile = false;
                }
                int numNormGen = input.ReadInt();
                if (numNormGen == NO)
                {
                    normGen = null;
                }
                else
                {
                    normGen = new long[numNormGen];
                    for (int j = 0; j < numNormGen; j++)
                    {
                        normGen[j] = input.ReadLong();
                    }
                }
                isCompoundFile = (sbyte)input.ReadByte();
                preLockless    = (isCompoundFile == CHECK_DIR);
                if (format <= SegmentInfos.FORMAT_DEL_COUNT)
                {
                    delCount = input.ReadInt();
                    System.Diagnostics.Debug.Assert(delCount <= docCount);
                }
                else
                {
                    delCount = -1;
                }
                if (format <= SegmentInfos.FORMAT_HAS_PROX)
                {
                    hasProx = input.ReadByte() == 1;
                }
                else
                {
                    hasProx = true;
                }

                if (format <= SegmentInfos.FORMAT_DIAGNOSTICS)
                {
                    diagnostics = input.ReadStringStringMap();
                }
                else
                {
                    diagnostics = new System.Collections.Generic.Dictionary <string, string>();
                }
            }
            else
            {
                delGen                 = CHECK_DIR;
                normGen                = null;
                isCompoundFile         = (sbyte)(CHECK_DIR);
                preLockless            = true;
                hasSingleNormFile      = false;
                docStoreOffset         = -1;
                docStoreIsCompoundFile = false;
                docStoreSegment        = null;
                delCount               = -1;
                hasProx                = true;
                diagnostics            = new System.Collections.Generic.Dictionary <string, string>();
            }
        }
Пример #11
0
        internal FieldsReader(Directory d, System.String segment, FieldInfos fn, int readBufferSize, int docStoreOffset, int size)
        {
            bool success = false;

            isOriginal = true;
            try
            {
                fieldInfos = fn;

                cloneableFieldsStream = d.OpenInput(segment + "." + IndexFileNames.FIELDS_EXTENSION, readBufferSize);
                cloneableIndexStream  = d.OpenInput(segment + "." + IndexFileNames.FIELDS_INDEX_EXTENSION, readBufferSize);

                // First version of fdx did not include a format
                // header, but, the first int will always be 0 in that
                // case
                int firstInt = cloneableIndexStream.ReadInt();
                if (firstInt == 0)
                {
                    format = 0;
                }
                else
                {
                    format = firstInt;
                }

                if (format > FieldsWriter.FORMAT_CURRENT &&
                    /* extra support for Lucene 3.0 indexes: */ format != FieldsWriter.FORMAT_LUCENE_3_0_NO_COMPRESSED_FIELDS
                    )
                {
                    throw new CorruptIndexException("Incompatible format version: " + format + " expected " + FieldsWriter.FORMAT_CURRENT + " or lower");
                }

                if (format > FieldsWriter.FORMAT)
                {
                    formatSize = 4;
                }
                else
                {
                    formatSize = 0;
                }

                if (format < FieldsWriter.FORMAT_VERSION_UTF8_LENGTH_IN_BYTES)
                {
                    cloneableFieldsStream.SetModifiedUTF8StringsMode();
                }

                fieldsStream = (IndexInput)cloneableFieldsStream.Clone();

                long indexSize = cloneableIndexStream.Length() - formatSize;

                if (docStoreOffset != -1)
                {
                    // We read only a slice out of this shared fields file
                    this.docStoreOffset = docStoreOffset;
                    this.size           = size;

                    // Verify the file is long enough to hold all of our
                    // docs
                    System.Diagnostics.Debug.Assert(((int)(indexSize / 8)) >= size + this.docStoreOffset, "indexSize=" + indexSize + " size=" + size + " docStoreOffset=" + docStoreOffset);
                }
                else
                {
                    this.docStoreOffset = 0;
                    this.size           = (int)(indexSize >> 3);
                }

                indexStream  = (IndexInput)cloneableIndexStream.Clone();
                numTotalDocs = (int)(indexSize >> 3);
                success      = true;
            }
            finally
            {
                // With lock-less commits, it's entirely possible (and
                // fine) to hit a FileNotFound exception above. In
                // this case, we want to explicitly close any subset
                // of things that were opened so that we don't have to
                // wait for a GC to do so.
                if (!success)
                {
                    Close();
                }
            }
        }
Пример #12
0
		private int CheckValidFormat(IndexInput in_Renamed)
		{
			int format = in_Renamed.ReadInt();
			if (format > FORMAT_CURRENT)
			{
				throw new CorruptIndexException("Incompatible format version: " + format + " expected " + FORMAT_CURRENT + " or less");
			}
			return format;
		}
Пример #13
0
        /// <summary>Returns a {@link Status} instance detailing
        /// the state of the index.
        ///
        /// </summary>
        /// <param name="onlySegments">list of specific segment names to check
        ///
        /// <p/>As this method checks every byte in the specified
        /// segments, on a large index it can take quite a long
        /// time to run.
        ///
        /// <p/><b>WARNING</b>: make sure
        /// you only call this when the index is not opened by any
        /// writer.
        /// </param>
        public virtual Status CheckIndex_Renamed_Method(System.Collections.IList onlySegments)
        {
            System.Globalization.NumberFormatInfo nf = System.Globalization.CultureInfo.CurrentCulture.NumberFormat;
            SegmentInfos sis    = new SegmentInfos();
            Status       result = new Status();

            result.dir = dir;
            try
            {
                sis.Read(dir);
            }
            catch (System.Exception t)
            {
                Msg("ERROR: could not read any segments file in directory");
                result.missingSegments = true;
                if (infoStream != null)
                {
                    infoStream.WriteLine(t.StackTrace);
                }
                return(result);
            }

            int numSegments = sis.Count;

            System.String segmentsFileName = sis.GetCurrentSegmentFileName();
            IndexInput    input            = null;

            try
            {
                input = dir.OpenInput(segmentsFileName);
            }
            catch (System.Exception t)
            {
                Msg("ERROR: could not open segments file in directory");
                if (infoStream != null)
                {
                    infoStream.WriteLine(t.StackTrace);
                }
                result.cantOpenSegments = true;
                return(result);
            }
            int format = 0;

            try
            {
                format = input.ReadInt();
            }
            catch (System.Exception t)
            {
                Msg("ERROR: could not read segment file version in directory");
                if (infoStream != null)
                {
                    infoStream.WriteLine(t.StackTrace);
                }
                result.missingSegmentVersion = true;
                return(result);
            }
            finally
            {
                if (input != null)
                {
                    input.Close();
                }
            }

            System.String sFormat = "";
            bool          skip    = false;

            if (format == SegmentInfos.FORMAT)
            {
                sFormat = "FORMAT [Lucene Pre-2.1]";
            }
            if (format == SegmentInfos.FORMAT_LOCKLESS)
            {
                sFormat = "FORMAT_LOCKLESS [Lucene 2.1]";
            }
            else if (format == SegmentInfos.FORMAT_SINGLE_NORM_FILE)
            {
                sFormat = "FORMAT_SINGLE_NORM_FILE [Lucene 2.2]";
            }
            else if (format == SegmentInfos.FORMAT_SHARED_DOC_STORE)
            {
                sFormat = "FORMAT_SHARED_DOC_STORE [Lucene 2.3]";
            }
            else
            {
                if (format == SegmentInfos.FORMAT_CHECKSUM)
                {
                    sFormat = "FORMAT_CHECKSUM [Lucene 2.4]";
                }
                else if (format == SegmentInfos.FORMAT_DEL_COUNT)
                {
                    sFormat = "FORMAT_DEL_COUNT [Lucene 2.4]";
                }
                else if (format == SegmentInfos.FORMAT_HAS_PROX)
                {
                    sFormat = "FORMAT_HAS_PROX [Lucene 2.4]";
                }
                else if (format == SegmentInfos.FORMAT_USER_DATA)
                {
                    sFormat = "FORMAT_USER_DATA [Lucene 2.9]";
                }
                else if (format == SegmentInfos.FORMAT_DIAGNOSTICS)
                {
                    sFormat = "FORMAT_DIAGNOSTICS [Lucene 2.9]";
                }
                else if (format < SegmentInfos.CURRENT_FORMAT)
                {
                    sFormat = "int=" + format + " [newer version of Lucene than this tool]";
                    skip    = true;
                }
                else
                {
                    sFormat = format + " [Lucene 1.3 or prior]";
                }
            }

            result.segmentsFileName = segmentsFileName;
            result.numSegments      = numSegments;
            result.segmentFormat    = sFormat;
            result.userData         = sis.GetUserData();
            System.String userDataString;
            if (sis.GetUserData().Count > 0)
            {
                userDataString = " userData=" + SupportClass.CollectionsHelper.CollectionToString(sis.GetUserData());
            }
            else
            {
                userDataString = "";
            }

            Msg("Segments file=" + segmentsFileName + " numSegments=" + numSegments + " version=" + sFormat + userDataString);

            if (onlySegments != null)
            {
                result.partial = true;
                if (infoStream != null)
                {
                    infoStream.Write("\nChecking only these segments:");
                }
                System.Collections.IEnumerator it = onlySegments.GetEnumerator();
                while (it.MoveNext())
                {
                    if (infoStream != null)
                    {
                        infoStream.Write(" " + it.Current);
                    }
                }
                System.Collections.IEnumerator e = onlySegments.GetEnumerator();
                while (e.MoveNext() == true)
                {
                    result.segmentsChecked.Add(e.Current);
                }
                Msg(":");
            }

            if (skip)
            {
                Msg("\nERROR: this index appears to be created by a newer version of Lucene than this tool was compiled on; please re-compile this tool on the matching version of Lucene; exiting");
                result.toolOutOfDate = true;
                return(result);
            }


            result.newSegments = (SegmentInfos)sis.Clone();
            result.newSegments.Clear();

            for (int i = 0; i < numSegments; i++)
            {
                SegmentInfo info = sis.Info(i);
                if (onlySegments != null && !onlySegments.Contains(info.name))
                {
                    continue;
                }
                Status.SegmentInfoStatus segInfoStat = new Status.SegmentInfoStatus();
                result.segmentInfos.Add(segInfoStat);
                Msg("  " + (1 + i) + " of " + numSegments + ": name=" + info.name + " docCount=" + info.docCount);
                segInfoStat.name     = info.name;
                segInfoStat.docCount = info.docCount;

                int toLoseDocCount = info.docCount;

                SegmentReader reader = null;

                try
                {
                    Msg("    compound=" + info.GetUseCompoundFile());
                    segInfoStat.compound = info.GetUseCompoundFile();
                    Msg("    hasProx=" + info.GetHasProx());
                    segInfoStat.hasProx = info.GetHasProx();
                    Msg("    numFiles=" + info.Files().Count);
                    segInfoStat.numFiles = info.Files().Count;
                    Msg(System.String.Format(nf, "    size (MB)={0:f}", new System.Object[] { (info.SizeInBytes() / (1024.0 * 1024.0)) }));
                    segInfoStat.sizeMB = info.SizeInBytes() / (1024.0 * 1024.0);
                    System.Collections.Generic.IDictionary <string, string> diagnostics = info.GetDiagnostics();
                    segInfoStat.diagnostics = diagnostics;
                    if (diagnostics.Count > 0)
                    {
                        Msg("    diagnostics = " + SupportClass.CollectionsHelper.CollectionToString(diagnostics));
                    }

                    int docStoreOffset = info.GetDocStoreOffset();
                    if (docStoreOffset != -1)
                    {
                        Msg("    docStoreOffset=" + docStoreOffset);
                        segInfoStat.docStoreOffset = docStoreOffset;
                        Msg("    docStoreSegment=" + info.GetDocStoreSegment());
                        segInfoStat.docStoreSegment = info.GetDocStoreSegment();
                        Msg("    docStoreIsCompoundFile=" + info.GetDocStoreIsCompoundFile());
                        segInfoStat.docStoreCompoundFile = info.GetDocStoreIsCompoundFile();
                    }
                    System.String delFileName = info.GetDelFileName();
                    if (delFileName == null)
                    {
                        Msg("    no deletions");
                        segInfoStat.hasDeletions = false;
                    }
                    else
                    {
                        Msg("    has deletions [delFileName=" + delFileName + "]");
                        segInfoStat.hasDeletions      = true;
                        segInfoStat.deletionsFileName = delFileName;
                    }
                    if (infoStream != null)
                    {
                        infoStream.Write("    test: open reader.........");
                    }
                    reader = SegmentReader.Get(info);

                    segInfoStat.openReaderPassed = true;

                    int numDocs = reader.NumDocs();
                    toLoseDocCount = numDocs;
                    if (reader.HasDeletions())
                    {
                        if (reader.deletedDocs.Count() != info.GetDelCount())
                        {
                            throw new System.SystemException("delete count mismatch: info=" + info.GetDelCount() + " vs deletedDocs.count()=" + reader.deletedDocs.Count());
                        }
                        if (reader.deletedDocs.Count() > reader.MaxDoc())
                        {
                            throw new System.SystemException("too many deleted docs: maxDoc()=" + reader.MaxDoc() + " vs deletedDocs.count()=" + reader.deletedDocs.Count());
                        }
                        if (info.docCount - numDocs != info.GetDelCount())
                        {
                            throw new System.SystemException("delete count mismatch: info=" + info.GetDelCount() + " vs reader=" + (info.docCount - numDocs));
                        }
                        segInfoStat.numDeleted = info.docCount - numDocs;
                        Msg("OK [" + (segInfoStat.numDeleted) + " deleted docs]");
                    }
                    else
                    {
                        if (info.GetDelCount() != 0)
                        {
                            throw new System.SystemException("delete count mismatch: info=" + info.GetDelCount() + " vs reader=" + (info.docCount - numDocs));
                        }
                        Msg("OK");
                    }
                    if (reader.MaxDoc() != info.docCount)
                    {
                        throw new System.SystemException("SegmentReader.maxDoc() " + reader.MaxDoc() + " != SegmentInfos.docCount " + info.docCount);
                    }

                    // Test getFieldNames()
                    if (infoStream != null)
                    {
                        infoStream.Write("    test: fields..............");
                    }
                    System.Collections.Generic.ICollection <string> fieldNames = reader.GetFieldNames(IndexReader.FieldOption.ALL);
                    Msg("OK [" + fieldNames.Count + " fields]");
                    segInfoStat.numFields = fieldNames.Count;

                    // Test Field Norms
                    segInfoStat.fieldNormStatus = TestFieldNorms(fieldNames, reader);

                    // Test the Term Index
                    segInfoStat.termIndexStatus = TestTermIndex(info, reader);

                    // Test Stored Fields
                    segInfoStat.storedFieldStatus = TestStoredFields(info, reader, nf);

                    // Test Term Vectors
                    segInfoStat.termVectorStatus = TestTermVectors(info, reader, nf);

                    // Rethrow the first exception we encountered
                    //  This will cause stats for failed segments to be incremented properly
                    if (segInfoStat.fieldNormStatus.error != null)
                    {
                        throw new System.SystemException("Field Norm test failed");
                    }
                    else if (segInfoStat.termIndexStatus.error != null)
                    {
                        throw new System.SystemException("Term Index test failed");
                    }
                    else if (segInfoStat.storedFieldStatus.error != null)
                    {
                        throw new System.SystemException("Stored Field test failed");
                    }
                    else if (segInfoStat.termVectorStatus.error != null)
                    {
                        throw new System.SystemException("Term Vector test failed");
                    }

                    Msg("");
                }
                catch (System.Exception t)
                {
                    Msg("FAILED");
                    System.String comment;
                    comment = "fixIndex() would remove reference to this segment";
                    Msg("    WARNING: " + comment + "; full exception:");
                    if (infoStream != null)
                    {
                        infoStream.WriteLine(t.StackTrace);
                    }
                    Msg("");
                    result.totLoseDocCount += toLoseDocCount;
                    result.numBadSegments++;
                    continue;
                }
                finally
                {
                    if (reader != null)
                    {
                        reader.Close();
                    }
                }

                // Keeper
                result.newSegments.Add(info.Clone());
            }

            if (0 == result.numBadSegments)
            {
                result.clean = true;
                Msg("No problems were detected with this index.\n");
            }
            else
            {
                Msg("WARNING: " + result.numBadSegments + " broken segments (containing " + result.totLoseDocCount + " documents) detected");
            }

            return(result);
        }
Пример #14
0
            public System.Object Run(IndexCommit commit)
            {
                if (commit != null)
                {
                    if (directory != commit.GetDirectory())
                    {
                        throw new System.IO.IOException("the specified commit does not match the specified Directory");
                    }
                    return(DoBody(commit.GetSegmentsFileName()));
                }

                System.String segmentFileName   = null;
                long          lastGen           = -1;
                long          gen               = 0;
                int           genLookaheadCount = 0;

                System.IO.IOException exc = null;
                bool retry = false;

                int method = 0;

                // 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, and
                // fall back to the third when necessary.

                while (true)
                {
                    if (0 == method)
                    {
                        // Method 1: 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):
                        System.String[] files = null;

                        long genA = -1;

                        files = directory.ListAll();

                        if (files != null)
                        {
                            genA = Mono.Lucene.Net.Index.SegmentInfos.GetCurrentSegmentGeneration(files);
                        }

                        Mono.Lucene.Net.Index.SegmentInfos.Message("directory listing genA=" + genA);

                        // Method 2: 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 < Mono.Lucene.Net.Index.SegmentInfos.defaultGenFileRetryCount; i++)
                        {
                            IndexInput genInput = null;
                            try
                            {
                                genInput = directory.OpenInput(IndexFileNames.SEGMENTS_GEN);
                            }
                            catch (System.IO.FileNotFoundException e)
                            {
                                Mono.Lucene.Net.Index.SegmentInfos.Message("segments.gen open: FileNotFoundException " + e);
                                break;
                            }
                            catch (System.IO.IOException e)
                            {
                                Mono.Lucene.Net.Index.SegmentInfos.Message("segments.gen open: IOException " + e);
                            }

                            if (genInput != null)
                            {
                                try
                                {
                                    int version = genInput.ReadInt();
                                    if (version == Mono.Lucene.Net.Index.SegmentInfos.FORMAT_LOCKLESS)
                                    {
                                        long gen0 = genInput.ReadLong();
                                        long gen1 = genInput.ReadLong();
                                        Mono.Lucene.Net.Index.SegmentInfos.Message("fallback check: " + gen0 + "; " + gen1);
                                        if (gen0 == gen1)
                                        {
                                            // The file is consistent.
                                            genB = gen0;
                                            break;
                                        }
                                    }
                                }
                                catch (System.IO.IOException err2)
                                {
                                    // will retry
                                }
                                finally
                                {
                                    genInput.Close();
                                }
                            }
                            try
                            {
                                System.Threading.Thread.Sleep(new System.TimeSpan((System.Int64) 10000 * Mono.Lucene.Net.Index.SegmentInfos.defaultGenFileRetryPauseMsec));
                            }
                            catch (System.Threading.ThreadInterruptedException ie)
                            {
                                // In 3.0 we will change this to throw
                                // InterruptedException instead
                                SupportClass.ThreadClass.Current().Interrupt();
                                throw new System.SystemException(ie.Message, ie);
                            }
                        }

                        Mono.Lucene.Net.Index.SegmentInfos.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
                            System.String s;
                            if (files != null)
                            {
                                s = "";
                                for (int i = 0; i < files.Length; i++)
                                {
                                    s += (" " + files[i]);
                                }
                            }
                            else
                            {
                                s = " null";
                            }
                            throw new System.IO.FileNotFoundException("no segments* file found in " + directory + ": files:" + s);
                        }
                    }

                    // Third method (fallback if first & second methods
                    // are not reliable): since both directory cache and
                    // file contents cache seem to be stale, just
                    // advance the generation.
                    if (1 == method || (0 == method && lastGen == gen && retry))
                    {
                        method = 1;

                        if (genLookaheadCount < Mono.Lucene.Net.Index.SegmentInfos.defaultGenLookaheadCount)
                        {
                            gen++;
                            genLookaheadCount++;
                            Mono.Lucene.Net.Index.SegmentInfos.Message("look ahead increment gen to " + gen);
                        }
                    }

                    if (lastGen == gen)
                    {
                        // This means we're about to try the same
                        // segments_N last tried.  This is allowed,
                        // exactly once, because writer could have been in
                        // the process of writing segments_N last time.

                        if (retry)
                        {
                            // OK, we've tried the same segments_N file
                            // twice in a row, so this must be a real
                            // error.  We throw the original exception we
                            // got.
                            throw exc;
                        }
                        else
                        {
                            retry = true;
                        }
                    }
                    else if (0 == method)
                    {
                        // Segment file has advanced since our last loop, so
                        // reset retry:
                        retry = false;
                    }

                    lastGen = gen;

                    segmentFileName = IndexFileNames.FileNameFromGeneration(IndexFileNames.SEGMENTS, "", gen);

                    try
                    {
                        System.Object v = DoBody(segmentFileName);
                        Mono.Lucene.Net.Index.SegmentInfos.Message("success on " + segmentFileName);

                        return(v);
                    }
                    catch (System.IO.IOException err)
                    {
                        // Save the original root cause:
                        if (exc == null)
                        {
                            exc = err;
                        }

                        Mono.Lucene.Net.Index.SegmentInfos.Message("primary Exception on '" + segmentFileName + "': " + err + "'; will retry: retry=" + retry + "; gen = " + gen);

                        if (!retry && gen > 1)
                        {
                            // This is our first time trying this segments
                            // file (because retry is false), and, there is
                            // possibly a segments_(N-1) (because gen > 1).
                            // So, check if the segments_(N-1) exists and
                            // try it if so:
                            System.String prevSegmentFileName = IndexFileNames.FileNameFromGeneration(IndexFileNames.SEGMENTS, "", gen - 1);

                            bool prevExists;
                            prevExists = directory.FileExists(prevSegmentFileName);

                            if (prevExists)
                            {
                                Mono.Lucene.Net.Index.SegmentInfos.Message("fallback to prior segment file '" + prevSegmentFileName + "'");
                                try
                                {
                                    System.Object v = DoBody(prevSegmentFileName);
                                    if (exc != null)
                                    {
                                        Mono.Lucene.Net.Index.SegmentInfos.Message("success on fallback " + prevSegmentFileName);
                                    }
                                    return(v);
                                }
                                catch (System.IO.IOException err2)
                                {
                                    Mono.Lucene.Net.Index.SegmentInfos.Message("secondary Exception on '" + prevSegmentFileName + "': " + err2 + "'; will retry");
                                }
                            }
                        }
                    }
                }
            }