Lucene.Net.Codecs.Lucene45: Fixed XML documentation comment warnings
Project: http://git-wip-us.apache.org/repos/asf/lucenenet/repo Commit: http://git-wip-us.apache.org/repos/asf/lucenenet/commit/b27d10c3 Tree: http://git-wip-us.apache.org/repos/asf/lucenenet/tree/b27d10c3 Diff: http://git-wip-us.apache.org/repos/asf/lucenenet/diff/b27d10c3 Branch: refs/heads/master Commit: b27d10c3b70b0136e45a9387a5cdab5777180211 Parents: 5478f1b Author: Shad Storhaug <[email protected]> Authored: Mon Jun 5 08:33:37 2017 +0700 Committer: Shad Storhaug <[email protected]> Committed: Tue Jun 6 06:58:40 2017 +0700 ---------------------------------------------------------------------- CONTRIBUTING.md | 3 +- src/Lucene.Net/Codecs/Lucene45/Lucene45Codec.cs | 23 +- .../Lucene45/Lucene45DocValuesConsumer.cs | 162 +------------- .../Codecs/Lucene45/Lucene45DocValuesFormat.cs | 221 ++++++++++--------- .../Lucene45/Lucene45DocValuesProducer.cs | 49 ++-- 5 files changed, 156 insertions(+), 302 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/lucenenet/blob/b27d10c3/CONTRIBUTING.md ---------------------------------------------------------------------- diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index 0d350a9..ce132b9 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -56,8 +56,7 @@ helpers to help with that, see for examples see our [Java style methods to avoid 3. Codecs.Lucene40 (namespace) 4. Codecs.Lucene41 (namespace) 5. Codecs.Lucene42 (namespace) - 6. Codecs.Lucene45 (namespace) - 7. Util.Packed (namespace) + 6. Util.Packed (namespace) 2. Lucene.Net.Codecs (project) 1. Appending (namespace) 2. BlockTerms (namespace) http://git-wip-us.apache.org/repos/asf/lucenenet/blob/b27d10c3/src/Lucene.Net/Codecs/Lucene45/Lucene45Codec.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net/Codecs/Lucene45/Lucene45Codec.cs b/src/Lucene.Net/Codecs/Lucene45/Lucene45Codec.cs index 8214bd6..b2ccca2 100644 --- a/src/Lucene.Net/Codecs/Lucene45/Lucene45Codec.cs +++ b/src/Lucene.Net/Codecs/Lucene45/Lucene45Codec.cs @@ -31,13 +31,14 @@ namespace Lucene.Net.Codecs.Lucene45 /// <summary> /// Implements the Lucene 4.5 index format, with configurable per-field postings /// and docvalues formats. - /// <p> + /// <para/> /// If you want to reuse functionality of this codec in another codec, extend - /// <seealso cref="FilterCodec"/>. + /// <see cref="FilterCodec"/>. + /// <para/> + /// See <see cref="Lucene.Net.Codecs.Lucene45"/> package documentation for file format details. + /// <para/> + /// @lucene.experimental /// </summary> - /// <seealso cref= Lucene.Net.Codecs.Lucene45 package documentation for file format details. - /// @lucene.experimental </seealso> - /// @deprecated Only for reading old 4.3-4.5 segments // NOTE: if we make largish changes in a minor release, easier to just make Lucene46Codec or whatever // if they are backwards compatible or smallish we can probably do the backwards in the postingsreader // (it writes a minor version, etc). @@ -126,9 +127,9 @@ namespace Lucene.Net.Codecs.Lucene45 /// <summary> /// Returns the postings format that should be used for writing - /// new segments of <code>field</code>. - /// - /// The default implementation always returns "Lucene41" + /// new segments of <paramref name="field"/>. + /// <para/> + /// The default implementation always returns "Lucene41" /// </summary> public virtual PostingsFormat GetPostingsFormatForField(string field) { @@ -137,9 +138,9 @@ namespace Lucene.Net.Codecs.Lucene45 /// <summary> /// Returns the docvalues format that should be used for writing - /// new segments of <code>field</code>. - /// - /// The default implementation always returns "Lucene45" + /// new segments of <paramref name="field"/>. + /// <para/> + /// The default implementation always returns "Lucene45" /// </summary> public virtual DocValuesFormat GetDocValuesFormatForField(string field) { http://git-wip-us.apache.org/repos/asf/lucenenet/blob/b27d10c3/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesConsumer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesConsumer.cs b/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesConsumer.cs index 76ebffa..9907b28 100644 --- a/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesConsumer.cs +++ b/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesConsumer.cs @@ -37,7 +37,7 @@ namespace Lucene.Net.Codecs.Lucene45 using StringHelper = Lucene.Net.Util.StringHelper; /// <summary> - /// writer for <seealso cref="Lucene45DocValuesFormat"/> </summary> + /// Writer for <see cref="Lucene45DocValuesFormat"/> </summary> public class Lucene45DocValuesConsumer : DocValuesConsumer, IDisposable { internal static readonly int BLOCK_SIZE = 16384; @@ -45,7 +45,7 @@ namespace Lucene.Net.Codecs.Lucene45 internal static readonly long MISSING_ORD = BitConverter.DoubleToInt64Bits(-1); /// <summary> - /// Compressed using packed blocks of ints. </summary> + /// Compressed using packed blocks of <see cref="int"/>s. </summary> public const int DELTA_COMPRESSED = 0; /// <summary> @@ -70,13 +70,13 @@ namespace Lucene.Net.Codecs.Lucene45 /// <summary> /// Standard storage for sorted set values with 1 level of indirection: - /// docId -> address -> ord. + /// docId -> address -> ord. /// </summary> public static readonly int SORTED_SET_WITH_ADDRESSES = 0; /// <summary> /// Single-valued sorted set values, encoded as sorted values, so no level - /// of indirection: docId -> ord. + /// of indirection: docId -> ord. /// </summary> public static readonly int SORTED_SET_SINGLE_VALUED_SORTED = 1; @@ -84,7 +84,7 @@ namespace Lucene.Net.Codecs.Lucene45 internal readonly int maxDoc; /// <summary> - /// expert: Creates a new writer </summary> + /// Expert: Creates a new writer. </summary> public Lucene45DocValuesConsumer(SegmentWriteState state, string dataCodec, string dataExtension, string metaCodec, string metaExtension) { bool success = false; @@ -353,7 +353,7 @@ namespace Lucene.Net.Codecs.Lucene45 } /// <summary> - /// expert: writes a value dictionary for a sorted/sortedset field </summary> + /// Expert: writes a value dictionary for a sorted/sortedset field. </summary> protected internal virtual void AddTermsDict(FieldInfo field, IEnumerable<BytesRef> values) { // first check if its a "fixed-length" terms dict @@ -498,156 +498,6 @@ namespace Lucene.Net.Codecs.Lucene45 Debug.Assert(!ordsIter.MoveNext()); } - /* - private class IterableAnonymousInnerClassHelper : IEnumerable<int> - { - private readonly Lucene45DocValuesConsumer OuterInstance; - - private IEnumerable<int> DocToOrdCount; - private IEnumerable<long> Ords; - - public IterableAnonymousInnerClassHelper(IEnumerable<int> docToOrdCount, IEnumerable<long> ords) - { - //this.OuterInstance = outerInstance; - this.DocToOrdCount = docToOrdCount; - this.Ords = ords; - } - - public virtual IEnumerator<BytesRef> GetEnumerator() - { - */ - /*IEnumerator<Number> docToOrdCountIt = DocToOrdCount.GetEnumerator(); - IEnumerator<Number> ordsIt = Ords.GetEnumerator(); - return new IteratorAnonymousInnerClassHelper(this, docToOrdCountIt, ordsIt);*/ - /* -return new SortedSetIterator(DocToOrdCount.GetEnumerator(), Ords.GetEnumerator()); -} - -System.Collections.IEnumerator System.Collections.IEnumerable.GetEnumerator() -{ -return GetEnumerator(); -} - -private class SortedSetIterator : IEnumerator<BytesRef> -{ -internal byte[] buffer = new byte[10]; //Initial size, will grow if needed -internal ByteArrayDataOutput output = new ByteArrayDataOutput(); -internal BytesRef bytesRef = new BytesRef(); - -internal IEnumerator<int> counts; -internal IEnumerator<long> ords; - -internal SortedSetIterator(IEnumerator<int> counts, IEnumerator<long> ords) -{ -this.counts = counts; -this.ords = ords; -} - -public BytesRef Current -{ -get -{ -return bytesRef; -} -} - -public void Dispose() -{ -counts.Dispose(); -ords.Dispose(); -} - -object System.Collections.IEnumerator.Current -{ -get { return bytesRef; } -} - -public bool MoveNext() -{ -if (!counts.MoveNext()) -return false; - -int count = counts.Current; -int maxSize = count * 9;//worst case -if (maxSize > buffer.Length) -buffer = ArrayUtil.Grow(buffer, maxSize); - -try -{ -EncodeValues(count); -} -catch (System.IO.IOException) -{ -throw; -} - -bytesRef.Bytes = buffer; -bytesRef.Offset = 0; -bytesRef.Length = output.Position; - -return true; -} - -private void EncodeValues(int count) -{ -output.Reset(buffer); -long lastOrd = 0; -for (int i = 0; i < count; i++) -{ -ords.MoveNext(); -long ord = ords.Current; -output.WriteVLong(ord - lastOrd); -lastOrd = ord; -} -} - -public void Reset() -{ -throw new NotImplementedException(); -} -}*/ - - /*private class IteratorAnonymousInnerClassHelper : IEnumerator<Number> - { - private readonly IterableAnonymousInnerClassHelper OuterInstance; - - private IEnumerator<Number> DocToOrdCountIt; - private IEnumerator<Number> OrdsIt; - - public IteratorAnonymousInnerClassHelper(IterableAnonymousInnerClassHelper outerInstance, IEnumerator<Number> docToOrdCountIt, IEnumerator<Number> ordsIt) - { - this.OuterInstance = outerInstance; - this.DocToOrdCountIt = docToOrdCountIt; - this.OrdsIt = ordsIt; - } - - public virtual bool HasNext() - { - return DocToOrdCountIt.HasNext(); - } - - public virtual Number Next() - { - Number ordCount = DocToOrdCountIt.next(); - if ((long)ordCount == 0) - { - return MISSING_ORD; - } - else - { - Debug.Assert((long)ordCount == 1); - return OrdsIt.next(); - } - } - - public virtual void Remove() - { - throw new System.NotSupportedException(); - } - }*/ - - //} - protected override void Dispose(bool disposing) { if (disposing) http://git-wip-us.apache.org/repos/asf/lucenenet/blob/b27d10c3/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesFormat.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesFormat.cs b/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesFormat.cs index 30cae45..780a2a1 100644 --- a/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesFormat.cs +++ b/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesFormat.cs @@ -22,130 +22,131 @@ namespace Lucene.Net.Codecs.Lucene45 /// <summary> /// Lucene 4.5 DocValues format. - /// <p> + /// <para/> /// Encodes the four per-document value types (Numeric,Binary,Sorted,SortedSet) with these strategies: - /// <p> - /// <seealso cref="DocValuesType#NUMERIC NUMERIC"/>: - /// <ul> - /// <li>Delta-compressed: per-document integers written in blocks of 16k. For each block + /// <para/> + /// <see cref="Index.DocValuesType.NUMERIC"/>: + /// <list type="bullet"> + /// <item><description>Delta-compressed: per-document integers written in blocks of 16k. For each block /// the minimum value in that block is encoded, and each entry is a delta from that /// minimum value. Each block of deltas is compressed with bitpacking. For more - /// information, see <seealso cref="BlockPackedWriter"/>. - /// <li>Table-compressed: when the number of unique values is very small (< 256), and - /// when there are unused "gaps" in the range of values used (such as <seealso cref="SmallFloat"/>), + /// information, see <see cref="Util.Packed.BlockPackedWriter"/>.</description></item> + /// <item><description>Table-compressed: when the number of unique values is very small (< 256), and + /// when there are unused "gaps" in the range of values used (such as <see cref="Util.SmallSingle"/>), /// a lookup table is written instead. Each per-document entry is instead the ordinal - /// to this table, and those ordinals are compressed with bitpacking (<seealso cref="PackedInts"/>). - /// <li>GCD-compressed: when all numbers share a common divisor, such as dates, the greatest - /// common denominator (GCD) is computed, and quotients are stored using Delta-compressed Numerics. - /// </ul> - /// <p> - /// <seealso cref="DocValuesType#BINARY BINARY"/>: - /// <ul> - /// <li>Fixed-width Binary: one large concatenated byte[] is written, along with the fixed length. - /// Each document's value can be addressed directly with multiplication ({@code docID * length}). - /// <li>Variable-width Binary: one large concatenated byte[] is written, along with end addresses + /// to this table, and those ordinals are compressed with bitpacking (<see cref="Util.Packed.PackedInt32s"/>).</description></item> + /// <item><description>GCD-compressed: when all numbers share a common divisor, such as dates, the greatest + /// common denominator (GCD) is computed, and quotients are stored using Delta-compressed Numerics.</description></item> + /// </list> + /// <para/> + /// <see cref="Index.DocValuesType.BINARY"/>: + /// <list type="bullet"> + /// <item><description>Fixed-width Binary: one large concatenated <see cref="T:byte[]"/> is written, along with the fixed length. + /// Each document's value can be addressed directly with multiplication (<c>docID * length</c>).</description></item> + /// <item><description>Variable-width Binary: one large concatenated <see cref="T:byte[]"/> is written, along with end addresses /// for each document. The addresses are written in blocks of 16k, with the current absolute /// start for the block, and the average (expected) delta per entry. For each document the - /// deviation from the delta (actual - expected) is written. - /// <li>Prefix-compressed Binary: values are written in chunks of 16, with the first value written - /// completely and other values sharing prefixes. chunk addresses are written in blocks of 16k, + /// deviation from the delta (actual - expected) is written.</description></item> + /// <item><description>Prefix-compressed Binary: values are written in chunks of 16, with the first value written + /// completely and other values sharing prefixes. Chunk addresses are written in blocks of 16k, /// with the current absolute start for the block, and the average (expected) delta per entry. - /// For each chunk the deviation from the delta (actual - expected) is written. - /// </ul> - /// <p> - /// <seealso cref="DocValuesType#SORTED SORTED"/>: - /// <ul> - /// <li>Sorted: a mapping of ordinals to deduplicated terms is written as Prefix-Compressed Binary, - /// along with the per-document ordinals written using one of the numeric strategies above. - /// </ul> - /// <p> - /// <seealso cref="DocValuesType#SORTED_SET SORTED_SET"/>: - /// <ul> - /// <li>SortedSet: a mapping of ordinals to deduplicated terms is written as Prefix-Compressed Binary, + /// For each chunk the deviation from the delta (actual - expected) is written.</description></item> + /// </list> + /// <para/> + /// <see cref="Index.DocValuesType.SORTED"/>: + /// <list type="bullet"> + /// <item><description>Sorted: a mapping of ordinals to deduplicated terms is written as Prefix-Compressed Binary, + /// along with the per-document ordinals written using one of the numeric strategies above.</description></item> + /// </list> + /// <para/> + /// <see cref="Index.DocValuesType.SORTED_SET"/>: + /// <list type="bullet"> + /// <item><description>SortedSet: a mapping of ordinals to deduplicated terms is written as Prefix-Compressed Binary, /// an ordinal list and per-document index into this list are written using the numeric strategies - /// above. - /// </ul> - /// <p> + /// above.</description></item> + /// </list> + /// <para/> /// Files: - /// <ol> - /// <li><tt>.dvd</tt>: DocValues data</li> - /// <li><tt>.dvm</tt>: DocValues metadata</li> - /// </ol> - /// <ol> - /// <li><a name="dvm" id="dvm"></a> - /// <p>The DocValues metadata or .dvm file.</p> - /// <p>For DocValues field, this stores metadata, such as the offset into the - /// DocValues data (.dvd)</p> - /// <p>DocValues metadata (.dvm) --> Header,<Entry><sup>NumFields</sup>,Footer</p> - /// <ul> - /// <li>Entry --> NumericEntry | BinaryEntry | SortedEntry | SortedSetEntry</li> - /// <li>NumericEntry --> GCDNumericEntry | TableNumericEntry | DeltaNumericEntry</li> - /// <li>GCDNumericEntry --> NumericHeader,MinValue,GCD</li> - /// <li>TableNumericEntry --> NumericHeader,TableSize,<seealso cref="DataOutput#writeLong Int64"/><sup>TableSize</sup></li> - /// <li>DeltaNumericEntry --> NumericHeader</li> - /// <li>NumericHeader --> FieldNumber,EntryType,NumericType,MissingOffset,PackedVersion,DataOffset,Count,BlockSize</li> - /// <li>BinaryEntry --> FixedBinaryEntry | VariableBinaryEntry | PrefixBinaryEntry</li> - /// <li>FixedBinaryEntry --> BinaryHeader</li> - /// <li>VariableBinaryEntry --> BinaryHeader,AddressOffset,PackedVersion,BlockSize</li> - /// <li>PrefixBinaryEntry --> BinaryHeader,AddressInterval,AddressOffset,PackedVersion,BlockSize</li> - /// <li>BinaryHeader --> FieldNumber,EntryType,BinaryType,MissingOffset,MinLength,MaxLength,DataOffset</li> - /// <li>SortedEntry --> FieldNumber,EntryType,BinaryEntry,NumericEntry</li> - /// <li>SortedSetEntry --> EntryType,BinaryEntry,NumericEntry,NumericEntry</li> - /// <li>FieldNumber,PackedVersion,MinLength,MaxLength,BlockSize,ValueCount --> <seealso cref="DataOutput#writeVInt VInt"/></li> - /// <li>EntryType,CompressionType --> <seealso cref="DataOutput#writeByte Byte"/></li> - /// <li>Header --> <seealso cref="CodecUtil#writeHeader CodecHeader"/></li> - /// <li>MinValue,GCD,MissingOffset,AddressOffset,DataOffset --> <seealso cref="DataOutput#writeLong Int64"/></li> - /// <li>TableSize --> <seealso cref="DataOutput#writeVInt vInt"/></li> - /// <li>Footer --> <seealso cref="CodecUtil#writeFooter CodecFooter"/></li> - /// </ul> - /// <p>Sorted fields have two entries: a BinaryEntry with the value metadata, - /// and an ordinary NumericEntry for the document-to-ord metadata.</p> - /// <p>SortedSet fields have three entries: a BinaryEntry with the value metadata, - /// and two NumericEntries for the document-to-ord-index and ordinal list metadata.</p> - /// <p>FieldNumber of -1 indicates the end of metadata.</p> - /// <p>EntryType is a 0 (NumericEntry) or 1 (BinaryEntry)</p> - /// <p>DataOffset is the pointer to the start of the data in the DocValues data (.dvd)</p> - /// <p>NumericType indicates how Numeric values will be compressed: - /// <ul> - /// <li>0 --> delta-compressed. For each block of 16k integers, every integer is delta-encoded - /// from the minimum value within the block. - /// <li>1 -->, gcd-compressed. When all integers share a common divisor, only quotients are stored - /// using blocks of delta-encoded ints. - /// <li>2 --> table-compressed. When the number of unique numeric values is small and it would save space, - /// a lookup table of unique values is written, followed by the ordinal for each document. - /// </ul> - /// <p>BinaryType indicates how Binary values will be stored: - /// <ul> - /// <li>0 --> fixed-width. All values have the same length, addressing by multiplication. - /// <li>1 -->, variable-width. An address for each value is stored. - /// <li>2 --> prefix-compressed. An address to the start of every interval'th value is stored. - /// </ul> - /// <p>MinLength and MaxLength represent the min and max byte[] value lengths for Binary values. + /// <list type="number"> + /// <item><description><c>.dvd</c>: DocValues data</description></item> + /// <item><description><c>.dvm</c>: DocValues metadata</description></item> + /// </list> + /// <list type="number"> + /// <item><description><a name="dvm" id="dvm"></a> + /// <para>The DocValues metadata or .dvm file.</para> + /// <para>For DocValues field, this stores metadata, such as the offset into the + /// DocValues data (.dvd)</para> + /// <para>DocValues metadata (.dvm) --> Header,<Entry><sup>NumFields</sup>,Footer</para> + /// <list type="bullet"> + /// <item><description>Entry --> NumericEntry | BinaryEntry | SortedEntry | SortedSetEntry</description></item> + /// <item><description>NumericEntry --> GCDNumericEntry | TableNumericEntry | DeltaNumericEntry</description></item> + /// <item><description>GCDNumericEntry --> NumericHeader,MinValue,GCD</description></item> + /// <item><description>TableNumericEntry --> NumericHeader,TableSize,Int64 (<see cref="Store.DataOutput.WriteInt64(long)"/>) <sup>TableSize</sup></description></item> + /// <item><description>DeltaNumericEntry --> NumericHeader</description></item> + /// <item><description>NumericHeader --> FieldNumber,EntryType,NumericType,MissingOffset,PackedVersion,DataOffset,Count,BlockSize</description></item> + /// <item><description>BinaryEntry --> FixedBinaryEntry | VariableBinaryEntry | PrefixBinaryEntry</description></item> + /// <item><description>FixedBinaryEntry --> BinaryHeader</description></item> + /// <item><description>VariableBinaryEntry --> BinaryHeader,AddressOffset,PackedVersion,BlockSize</description></item> + /// <item><description>PrefixBinaryEntry --> BinaryHeader,AddressInterval,AddressOffset,PackedVersion,BlockSize</description></item> + /// <item><description>BinaryHeader --> FieldNumber,EntryType,BinaryType,MissingOffset,MinLength,MaxLength,DataOffset</description></item> + /// <item><description>SortedEntry --> FieldNumber,EntryType,BinaryEntry,NumericEntry</description></item> + /// <item><description>SortedSetEntry --> EntryType,BinaryEntry,NumericEntry,NumericEntry</description></item> + /// <item><description>FieldNumber,PackedVersion,MinLength,MaxLength,BlockSize,ValueCount --> VInt (<see cref="Store.DataOutput.WriteVInt32(int)"/></description></item> + /// <item><description>EntryType,CompressionType --> Byte (<see cref="Store.DataOutput.WriteByte(byte)"/></description></item> + /// <item><description>Header --> CodecHeader (<see cref="CodecUtil.WriteHeader(Store.DataOutput, string, int)"/>) </description></item> + /// <item><description>MinValue,GCD,MissingOffset,AddressOffset,DataOffset --> Int64 (<see cref="Store.DataOutput.WriteInt64(long)"/>) </description></item> + /// <item><description>TableSize --> vInt (<see cref="Store.DataOutput.WriteVInt32(int)"/>) </description></item> + /// <item><description>Footer --> CodecFooter (<see cref="CodecUtil.WriteFooter(Store.IndexOutput)"/>) </description></item> + /// </list> + /// <para>Sorted fields have two entries: a <see cref="Lucene45DocValuesProducer.BinaryEntry"/> with the value metadata, + /// and an ordinary <see cref="Lucene45DocValuesProducer.NumericEntry"/> for the document-to-ord metadata.</para> + /// <para>SortedSet fields have three entries: a <see cref="Lucene45DocValuesProducer.BinaryEntry"/> with the value metadata, + /// and two <see cref="Lucene45DocValuesProducer.NumericEntry"/>s for the document-to-ord-index and ordinal list metadata.</para> + /// <para>FieldNumber of -1 indicates the end of metadata.</para> + /// <para>EntryType is a 0 (<see cref="Lucene45DocValuesProducer.NumericEntry"/>) or 1 (<see cref="Lucene45DocValuesProducer.BinaryEntry"/>)</para> + /// <para>DataOffset is the pointer to the start of the data in the DocValues data (.dvd)</para> + /// <para/>NumericType indicates how Numeric values will be compressed: + /// <list type="bullet"> + /// <item><description>0 --> delta-compressed. For each block of 16k integers, every integer is delta-encoded + /// from the minimum value within the block.</description></item> + /// <item><description>1 --> gcd-compressed. When all integers share a common divisor, only quotients are stored + /// using blocks of delta-encoded ints.</description></item> + /// <item><description>2 --> table-compressed. When the number of unique numeric values is small and it would save space, + /// a lookup table of unique values is written, followed by the ordinal for each document.</description></item> + /// </list> + /// <para/>BinaryType indicates how Binary values will be stored: + /// <list type="bullet"> + /// <item><description>0 --> fixed-width. All values have the same length, addressing by multiplication.</description></item> + /// <item><description>1 --> variable-width. An address for each value is stored.</description></item> + /// <item><description>2 --> prefix-compressed. An address to the start of every interval'th value is stored.</description></item> + /// </list> + /// <para/>MinLength and MaxLength represent the min and max byte[] value lengths for Binary values. /// If they are equal, then all values are of a fixed size, and can be addressed as DataOffset + (docID * length). /// Otherwise, the binary values are of variable size, and packed integer metadata (PackedVersion,BlockSize) /// is written for the addresses. - /// <p>MissingOffset points to a byte[] containing a bitset of all documents that had a value for the field. + /// <para/>MissingOffset points to a <see cref="T:byte[]"/> containing a bitset of all documents that had a value for the field. /// If its -1, then there are no missing values. - /// <p>Checksum contains the CRC32 checksum of all bytes in the .dvm file up + /// <para/>Checksum contains the CRC32 checksum of all bytes in the .dvm file up /// until the checksum. this is used to verify integrity of the file on opening the - /// index. - /// <li><a name="dvd" id="dvd"></a> - /// <p>The DocValues data or .dvd file.</p> - /// <p>For DocValues field, this stores the actual per-document data (the heavy-lifting)</p> - /// <p>DocValues data (.dvd) --> Header,<NumericData | BinaryData | SortedData><sup>NumFields</sup>,Footer</p> - /// <ul> - /// <li>NumericData --> DeltaCompressedNumerics | TableCompressedNumerics | GCDCompressedNumerics</li> - /// <li>BinaryData --> <seealso cref="DataOutput#writeByte Byte"/><sup>DataLength</sup>,Addresses</li> - /// <li>SortedData --> <seealso cref="FST FST<Int64>"/></li> - /// <li>DeltaCompressedNumerics --> <seealso cref="BlockPackedWriter BlockPackedInts(blockSize=16k)"/></li> - /// <li>TableCompressedNumerics --> <seealso cref="PackedInts PackedInts"/></li> - /// <li>GCDCompressedNumerics --> <seealso cref="BlockPackedWriter BlockPackedInts(blockSize=16k)"/></li> - /// <li>Addresses --> <seealso cref="MonotonicBlockPackedWriter MonotonicBlockPackedInts(blockSize=16k)"/></li> - /// <li>Footer --> <seealso cref="CodecUtil#writeFooter CodecFooter"/></li> - /// </ul> - /// <p>SortedSet entries store the list of ordinals in their BinaryData as a - /// sequences of increasing <seealso cref="DataOutput#writeVLong vLong"/>s, delta-encoded.</p> - /// </ol> + /// index.</description></item> + /// <item><description><a name="dvd" id="dvd"></a> + /// <para>The DocValues data or .dvd file.</para> + /// <para>For DocValues field, this stores the actual per-document data (the heavy-lifting)</para> + /// <para>DocValues data (.dvd) --> Header,<NumericData | BinaryData | SortedData><sup>NumFields</sup>,Footer</para> + /// <list type="bullet"> + /// <item><description>NumericData --> DeltaCompressedNumerics | TableCompressedNumerics | GCDCompressedNumerics</description></item> + /// <item><description>BinaryData --> Byte (<see cref="Store.DataOutput.WriteByte(byte)"/>) <sup>DataLength</sup>,Addresses</description></item> + /// <item><description>SortedData --> FST<Int64> (<see cref="Util.Fst.FST{T}"/>) </description></item> + /// <item><description>DeltaCompressedNumerics --> BlockPackedInts(blockSize=16k) (<see cref="Util.Packed.BlockPackedWriter"/>) </description></item> + /// <item><description>TableCompressedNumerics --> PackedInts (<see cref="Util.Packed.PackedInt32s"/>) </description></item> + /// <item><description>GCDCompressedNumerics --> BlockPackedInts(blockSize=16k) (<see cref="Util.Packed.BlockPackedWriter"/>) </description></item> + /// <item><description>Addresses --> MonotonicBlockPackedInts(blockSize=16k) (<see cref="Util.Packed.MonotonicBlockPackedWriter"/>) </description></item> + /// <item><description>Footer --> CodecFooter (<see cref="CodecUtil.WriteFooter(Store.IndexOutput)"/>) </description></item> + /// </list> + /// <para>SortedSet entries store the list of ordinals in their BinaryData as a + /// sequences of increasing vLongs (<see cref="Store.DataOutput.WriteVInt64(long)"/>), delta-encoded.</para></description></item> + /// </list> + /// <para/> /// @lucene.experimental /// </summary> [DocValuesFormatName("Lucene45")] // LUCENENET specific - using DocValuesFormatName attribute to ensure the default name passed from subclasses is the same as this class name http://git-wip-us.apache.org/repos/asf/lucenenet/blob/b27d10c3/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesProducer.cs ---------------------------------------------------------------------- diff --git a/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesProducer.cs b/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesProducer.cs index 025af22..300b1cf 100644 --- a/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesProducer.cs +++ b/src/Lucene.Net/Codecs/Lucene45/Lucene45DocValuesProducer.cs @@ -49,7 +49,7 @@ namespace Lucene.Net.Codecs.Lucene45 using TermsEnum = Lucene.Net.Index.TermsEnum; /// <summary> - /// reader for <seealso cref="Lucene45DocValuesFormat"/> </summary> + /// Reader for <see cref="Lucene45DocValuesFormat"/>. </summary> public class Lucene45DocValuesProducer : DocValuesProducer, IDisposable { private readonly IDictionary<int, NumericEntry> numerics; @@ -68,7 +68,7 @@ namespace Lucene.Net.Codecs.Lucene45 private readonly IDictionary<int, MonotonicBlockPackedReader> ordIndexInstances = new Dictionary<int, MonotonicBlockPackedReader>(); /// <summary> - /// expert: instantiates a new reader </summary> + /// Expert: instantiates a new reader. </summary> protected internal Lucene45DocValuesProducer(SegmentReadState state, string dataCodec, string dataExtension, string metaCodec, string metaExtension) { string metaName = IndexFileNames.SegmentFileName(state.SegmentInfo.Name, state.SegmentSuffix, metaExtension); @@ -502,8 +502,9 @@ namespace Lucene.Net.Codecs.Lucene45 } /// <summary> - /// returns an address instance for variable-length binary values. - /// @lucene.internal + /// Returns an address instance for variable-length binary values. + /// <para/> + /// @lucene.internal /// </summary> protected internal virtual MonotonicBlockPackedReader GetAddressInstance(IndexInput data, FieldInfo field, BinaryEntry bytes) { @@ -572,7 +573,8 @@ namespace Lucene.Net.Codecs.Lucene45 } /// <summary> - /// returns an address instance for prefix-compressed binary values. + /// Returns an address instance for prefix-compressed binary values. + /// <para/> /// @lucene.internal /// </summary> protected internal virtual MonotonicBlockPackedReader GetIntervalInstance(IndexInput data, FieldInfo field, BinaryEntry bytes) @@ -684,7 +686,8 @@ namespace Lucene.Net.Codecs.Lucene45 } /// <summary> - /// returns an address instance for sortedset ordinal lists + /// Returns an address instance for sortedset ordinal lists. + /// <para/> /// @lucene.internal /// </summary> protected internal virtual MonotonicBlockPackedReader GetOrdIndexInstance(IndexInput data, FieldInfo field, NumericEntry entry) @@ -895,7 +898,7 @@ namespace Lucene.Net.Codecs.Lucene45 } /// <summary> - /// metadata entry for a numeric docvalues field </summary> + /// Metadata entry for a numeric docvalues field. </summary> protected internal class NumericEntry { internal NumericEntry() @@ -903,28 +906,28 @@ namespace Lucene.Net.Codecs.Lucene45 } /// <summary> - /// offset to the bitset representing docsWithField, or -1 if no documents have missing values </summary> + /// Offset to the bitset representing docsWithField, or -1 if no documents have missing values. </summary> internal long missingOffset; /// <summary> - /// offset to the actual numeric values </summary> + /// Offset to the actual numeric values. </summary> public long Offset { get; set; } internal int format; /// <summary> - /// packed ints version used to encode these numerics + /// Packed <see cref="int"/>s version used to encode these numerics. /// <para/> /// NOTE: This was packedIntsVersion (field) in Lucene /// </summary> public int PackedInt32sVersion { get; set; } /// <summary> - /// count of values written </summary> + /// Count of values written. </summary> public long Count { get; set; } /// <summary> - /// packed ints blocksize </summary> + /// Packed <see cref="int"/>s blocksize. </summary> public int BlockSize { get; set; } internal long minValue; @@ -933,7 +936,7 @@ namespace Lucene.Net.Codecs.Lucene45 } /// <summary> - /// metadata entry for a binary docvalues field </summary> + /// Metadata entry for a binary docvalues field. </summary> protected internal class BinaryEntry { internal BinaryEntry() @@ -941,44 +944,44 @@ namespace Lucene.Net.Codecs.Lucene45 } /// <summary> - /// offset to the bitset representing docsWithField, or -1 if no documents have missing values </summary> + /// Offset to the bitset representing docsWithField, or -1 if no documents have missing values. </summary> internal long missingOffset; /// <summary> - /// offset to the actual binary values </summary> + /// Offset to the actual binary values. </summary> internal long offset; internal int format; /// <summary> - /// count of values written </summary> + /// Count of values written. </summary> public long Count { get; set; } internal int minLength; internal int maxLength; /// <summary> - /// offset to the addressing data that maps a value to its slice of the byte[] </summary> + /// Offset to the addressing data that maps a value to its slice of the <see cref="T:byte[]"/>. </summary> public long AddressesOffset { get; set; } /// <summary> - /// interval of shared prefix chunks (when using prefix-compressed binary) </summary> + /// Interval of shared prefix chunks (when using prefix-compressed binary). </summary> public long AddressInterval { get; set; } /// <summary> - /// packed ints version used to encode addressing information + /// Packed ints version used to encode addressing information. /// <para/> - /// NOTE: This was packedIntsVersion (field) in Lucene + /// NOTE: This was packedIntsVersion (field) in Lucene. /// </summary> public int PackedInt32sVersion { get; set; } /// <summary> - /// packed ints blocksize </summary> + /// Packed ints blocksize. </summary> public int BlockSize { get; set; } } /// <summary> - /// metadata entry for a sorted-set docvalues field </summary> + /// Metadata entry for a sorted-set docvalues field. </summary> protected internal class SortedSetEntry { internal SortedSetEntry() @@ -990,7 +993,7 @@ namespace Lucene.Net.Codecs.Lucene45 // internally we compose complex dv (sorted/sortedset) from other ones /// <summary> - /// NOTE: This was LongBinaryDocValues in Lucene + /// NOTE: This was LongBinaryDocValues in Lucene. /// </summary> internal abstract class Int64BinaryDocValues : BinaryDocValues {
