mirror of https://github.com/apache/lucene.git
LUCENE-3982: improve javadocs
git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/branches/pforcodec_3892@1374573 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Michael McCandless
parent
6d86815f65
commit
dddbe41902
|
|
@ -26,6 +26,8 @@ import org.apache.lucene.util.MathUtil;
|
|||
/**
|
||||
* This abstract class writes skip lists with multiple levels.
|
||||
*
|
||||
* <pre>
|
||||
*
|
||||
* Example for skipInterval = 3:
|
||||
* c (skip level 2)
|
||||
* c c c (skip level 1)
|
||||
|
|
@ -45,6 +47,7 @@ import org.apache.lucene.util.MathUtil;
|
|||
*
|
||||
* While this class takes care of writing the different skip levels,
|
||||
* subclasses must define the actual format of the skip data.
|
||||
* </pre>
|
||||
* @lucene.experimental
|
||||
*/
|
||||
|
||||
|
|
|
|||
|
|
@ -30,10 +30,290 @@ import org.apache.lucene.index.SegmentReadState;
|
|||
import org.apache.lucene.index.SegmentWriteState;
|
||||
import org.apache.lucene.util.IOUtils;
|
||||
|
||||
// javadocs
|
||||
import org.apache.lucene.codecs.MultiLevelSkipListWriter;
|
||||
import org.apache.lucene.codecs.CodecUtil;
|
||||
import org.apache.lucene.codecs.lucene40.Lucene40PostingsFormat;
|
||||
import org.apache.lucene.store.DataOutput;
|
||||
import org.apache.lucene.index.DocsEnum;
|
||||
import org.apache.lucene.index.FieldInfo.IndexOptions;
|
||||
import org.apache.lucene.index.FieldInfos;
|
||||
import org.apache.lucene.util.fst.FST;
|
||||
import org.apache.lucene.util.packed.PackedInts;
|
||||
|
||||
/**
|
||||
* Encodes/decode postings in packed int blocks for faster
|
||||
* decode.
|
||||
* Block postings format, which encodes postings in packed int blocks
|
||||
* for faster decode.
|
||||
*
|
||||
* <p>
|
||||
* Basic idea:
|
||||
* <ul>
|
||||
* <li>
|
||||
* <b>Packed Block and VInt Block</b>:
|
||||
* <p>In packed block, integers are encoded with the same bit width ({@link PackedInts packed format}),
|
||||
* the block size (i.e. number of integers inside block) is fixed. </p>
|
||||
* <p>In VInt block, integers are encoded as {@link DataOutput#writeVInt VInt},
|
||||
* the block size is variable.</p>
|
||||
* </li>
|
||||
*
|
||||
* <li>
|
||||
* <b>Block structure</b>:
|
||||
* <p>When the postings is long enough, BlockPostingsFormat will try to encode most integer data
|
||||
* as packed block.</p>
|
||||
* <p>Take a term with 259 documents as example, the first 256 document ids are encoded as two packed
|
||||
* blocks, while the remaining 3 as one VInt block. </p>
|
||||
* <p>Different kinds of data are always encoded separately into different packed blocks, but may
|
||||
* possible be encoded into a same VInt block. </p>
|
||||
* <p>This strategy is applied to pairs:
|
||||
* <document number, frequency>,
|
||||
* <position, payload length>,
|
||||
* <position, offset start, offset length>, and
|
||||
* <position, payload length, offsetstart, offset length>.</p>
|
||||
* </li>
|
||||
*
|
||||
* <li>
|
||||
* <b>Skipper setting</b>:
|
||||
* <p>The structure of skip table is quite similar to Lucene40PostingsFormat. Skip interval is the
|
||||
* same as block size, and each skip entry points to the beginning of each block. However, for
|
||||
* the first block, skip data is omitted.</p>
|
||||
* </li>
|
||||
*
|
||||
* <li>
|
||||
* <b>Positions, Payloads, and Offsets</b>:
|
||||
* <p>A position is an integer indicating where the term occured in one document.
|
||||
* A payload is a blob of metadata associated with current position.
|
||||
* An offset is a pair of integers indicating the tokenized start/end offsets for given term
|
||||
* in current position. </p>
|
||||
* <p>When payloads and offsets are not omitted, numPositions==numPayloads==numOffsets (assuming a
|
||||
* null payload contributes one count). As mentioned in block structure, it is possible to encode
|
||||
* these three either centralizedly or separately.
|
||||
* <p>For all the cases, payloads and offsets are stored together. When encoded as packed block,
|
||||
* position data is separated out as .pos, while payloads and offsets are encoded in .pay (payload
|
||||
* metadata will also be stored directly in .pay). When encoded as VInt block, all these three are
|
||||
* stored in .pos (so as payload metadata).</p>
|
||||
* </li>
|
||||
* </ul>
|
||||
* </p>
|
||||
*
|
||||
* <p>
|
||||
* Files and detailed format:
|
||||
* <ul>
|
||||
* <li><tt>.tim</tt>: <a href="#Termdictionary">Term Dictionary</a></li>
|
||||
* <li><tt>.tip</tt>: <a href="#Termindex">Term Index</a></li>
|
||||
* <li><tt>.doc</tt>: <a href="#Frequencies">Frequencies and Skip Data</a></li>
|
||||
* <li><tt>.pos</tt>: <a href="#Positions">Positions</a></li>
|
||||
* <li><tt>.pay</tt>: <a href="#Payloads">Payloads and Offsets</a></li>
|
||||
* </ul>
|
||||
* </p>
|
||||
*
|
||||
* <a name="Termdictionary" id="Termdictionary"></a>
|
||||
* <dl>
|
||||
* <dd>
|
||||
* <b>Term Dictionary</b>
|
||||
*
|
||||
* <p>The .tim file format is quite similar to Lucene40PostingsFormat,
|
||||
* with minor difference in MetadataBlock</p>
|
||||
*
|
||||
* <ul>
|
||||
* <!-- TODO: expand on this, its not really correct and doesnt explain sub-blocks etc -->
|
||||
* <li>TermDictionary(.tim) --> Header, DirOffset, PostingsHeader, PackedBlockSize,
|
||||
* <Block><sup>NumBlocks</sup>, FieldSummary</li>
|
||||
* <li>Block --> SuffixBlock, StatsBlock, MetadataBlock</li>
|
||||
* <li>SuffixBlock --> EntryCount, SuffixLength, Byte<sup>SuffixLength</sup></li>
|
||||
* <li>StatsBlock --> StatsLength, <DocFreq, TotalTermFreq><sup>EntryCount</sup></li>
|
||||
* <li>MetadataBlock --> MetaLength, <DocFPDelta,
|
||||
* <PosFPDelta, PosBlockFPDelta?, PayFPDelta?>?,
|
||||
* SkipFPDelta? ><sup>EntryCount</sup></li>
|
||||
* <li>FieldSummary --> NumFields, <FieldNumber, NumTerms, RootCodeLength,
|
||||
* Byte<sup>RootCodeLength</sup>, SumDocFreq, DocCount>
|
||||
* <sup>NumFields</sup></li>
|
||||
* <li>Header, PostingsHeader --> {@link CodecUtil#writeHeader CodecHeader}</li>
|
||||
* <li>DirOffset --> {@link DataOutput#writeLong Uint64}</li>
|
||||
* <li>PackedBlockSize, EntryCount, SuffixLength, StatsLength, DocFreq, MetaLength,
|
||||
* PosBlockFPDelta, SkipFPDelta, NumFields, FieldNumber, RootCodeLength, DocCount -->
|
||||
* {@link DataOutput#writeVInt VInt}</li>
|
||||
* <li>TotalTermFreq, DocFPDelta, PosFPDelta, NumTerms, SumTotalTermFreq, SumDocFreq -->
|
||||
* {@link DataOutput#writeVLong VLong}</li>
|
||||
* </ul>
|
||||
* <p>Notes:</p>
|
||||
* <ul>
|
||||
* <li>Here explains MetadataBlock only, other fields are mentioned in
|
||||
* <!--NOTE: change this manual html link, when directory structure is changed. -->
|
||||
* <a href="../../../../../org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.html#Termdictionary">Lucene40PostingsFormat:TermDictionary</a>
|
||||
* </li>
|
||||
* <li>PackedBlockSize is fixed block size for packed blocks. In packed block, bit width is
|
||||
* determined by the largest integer. Smaller block size result in smaller variance among width
|
||||
* of integers hence smaller indexes. Larger block size result in more efficient bulk i/o hence
|
||||
* better acceleration. This value should always be a multiple of 64, currently fixed as 128 as
|
||||
* a tradeoff. It is also the skip interval used to accerlerate {@link DocsEnum#advance(int)}.
|
||||
* <li>DocFPDelta determines the position of this term's TermFreqs within the .doc file.
|
||||
* In particular, it is the difference of file offset between this term's
|
||||
* data and previous term's data (or zero, for the first term in the block).</li>
|
||||
* <li>PayFPDelta determines the position of this term's payload or offset data within the .pay file.
|
||||
* Similar to DocFPDelta, it is the difference between two file positions (or neglected,
|
||||
* for fields that omit payloads and offsets, or for the first term in the block).</li>
|
||||
* <!--TODO: not quite sure, what is the difference?-->
|
||||
* <li>PosFPDelta and PosBlockFPDelta determine the position of this term's TermPositions within
|
||||
* the .pos file.
|
||||
* <li>PosBlockFPDelta determines the position of this term's TermPositions within the .pos file.
|
||||
* Similar to DocFPDelta, it is the difference between two file positions (or neglected,
|
||||
* for fields that omit position data, or for the first term in the block).</li>
|
||||
* <li>SkipFPDelta determines the position of this term's SkipData within the .doc
|
||||
* file. In particular, it is the number of bytes after TermFreqs that the
|
||||
* SkipData starts. In other words, it is the length of the TermFreq data.
|
||||
* SkipDelta is only stored if DocFreq is not smaller than SkipMinimum,
|
||||
* (i.e. 8 in BlockPostingsFormat).</li>
|
||||
* </ul>
|
||||
* </dd>
|
||||
* </dl>
|
||||
*
|
||||
* <a name="Termindex" id="Termindex"></a>
|
||||
* <dl>
|
||||
* <dd>
|
||||
* <b>Term Index</b>
|
||||
* <p>The .tim file format is mentioned in
|
||||
* <!--NOTE: change this manual html link, when directory structure is changed. -->
|
||||
* <a href="../../../../../org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.html#Termindex">Lucene40PostingsFormat:TermIndex</a>
|
||||
* </dd>
|
||||
* </dl>
|
||||
*
|
||||
*
|
||||
* <a name="Frequencies" id="Frequencies"></a>
|
||||
* <dl>
|
||||
* <dd>
|
||||
* <b>Frequencies and Skip Data</b>
|
||||
*
|
||||
* <p>The .doc file contains the lists of documents which contain each term, along
|
||||
* with the frequency of the term in that document (except when frequencies are
|
||||
* omitted: {@link IndexOptions#DOCS_ONLY}). It also saves skip data to the beginning of
|
||||
* each packed or VInt block, when the length of document list is larger than packed block size.</p>
|
||||
*
|
||||
* <ul>
|
||||
* <li>docFile(.doc) --> Header, < TermFreqs, SkipData? ><sup>TermCount</sup></li>
|
||||
* <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
|
||||
* <li>TermFreqs --> < PackedBlock > <sup>PackedDocBlockNum</sup>,
|
||||
* VIntBlock? </li>
|
||||
* <li>PackedBlock --> PackedDocDeltaBlock, PackedFreqBlock?
|
||||
* <li>VIntBlock --> < DocDelta[, Freq?] ><sup>DocFreq-PackedBlockSize*PackedDocBlockNum</sup>
|
||||
* <li>SkipData --> <<SkipLevelLength, SkipLevel>
|
||||
* <sup>NumSkipLevels-1</sup>, SkipLevel> <SkipDatum?></li>
|
||||
* <li>SkipLevel --> <SkipDatum> <sup>TrimmedDocFreq/(PackedBlockSize^(Level + 1))</sup></li>
|
||||
* <li>SkipDatum --> DocSkip, DocFPSkip, < PosFPSkip, PosBlockOffset, PayLength?,
|
||||
* OffsetStart?, PayFPSkip? >?, SkipChildLevelPointer?</li>
|
||||
* <li>PackedDocDeltaBlock, PackedFreqBlock --> {@link PackedInts PackedInts}</li>
|
||||
* <li>DocDelta,Freq,DocSkip,DocFPSkip,PosFPSkip,PosBlockOffset,PayLength,OffsetStart,PayFPSkip -->
|
||||
* {@link DataOutput#writeVInt VInt}</li>
|
||||
* <li>SkipChildLevelPointer --> {@link DataOutput#writeVLong VLong}</li>
|
||||
* </ul>
|
||||
* <p>Notes:</p>
|
||||
* <ul>
|
||||
* <li>PackedDocDeltaBlock is theoretically generated from two steps:
|
||||
* <ol>
|
||||
* <li>Calculate the difference between each document number and previous one,
|
||||
* and get a d-gaps list (for the first document, use absolute value); </li>
|
||||
* <li>For those d-gaps from first one to PackedDocBlockNum*PackedBlockSize<sup>th</sup>,
|
||||
* seperately encode as packed blocks.</li>
|
||||
* </ol>
|
||||
* If frequencies are not omitted, PackedFreqBlock will be generated without d-gap step.
|
||||
* </li>
|
||||
* <li>VIntBlock stores remaining d-gaps (along with frequencies when possible) with a format
|
||||
* mentioned in
|
||||
* <!--NOTE: change this manual html link, when directory structure is changed. -->
|
||||
* <a href="../../../../../org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.html#Frequencies">Lucene40PostingsFormat:Frequencies</a>
|
||||
* </li>
|
||||
* <li>PackedDocBlockNum is the number of packed blocks for current term's docids or frequencies.
|
||||
* In particular, PackedDocBlockNum = floor(DocFreq/PackedBlockSize) </li>
|
||||
* <li>TrimmedDocFreq = DocFreq % PackedBlockSize == 0 ? DocFreq - 1 : DocFreq.
|
||||
* We use this trick since the definition of skip entry is a little different from base interface.
|
||||
* In {@link MultiLevelSkipListWriter}, skip data is assumed to be saved for
|
||||
* skipInterval<sup>th</sup>, 2*skipInterval<sup>th</sup> ... posting in the list. However,
|
||||
* in BlockPostingsFormat, the skip data is saved for skipInterval+1<sup>th</sup>,
|
||||
* 2*skipInterval+1<sup>th</sup> ... posting (skipInterval==PackedBlockSize in this case).
|
||||
* When DocFreq is multiple of PackedBlockSize, MultiLevelSkipListWriter will expect one
|
||||
* more skip data than BlockSkipWriter. </li>
|
||||
* <li>SkipDatum is the metadata of one skip entry.
|
||||
* For the first block (no matter packed or VInt), it is omitted.</li>
|
||||
* <li>DocSkip records the document number of every PackedBlockSize<sup>th</sup> document number in
|
||||
* the postings(i.e. last document number in each packed block). On disk it is stored as the
|
||||
* difference from previous value in the sequence. </li>
|
||||
* <li>DocFPSkip records the file offsets of each block (excluding )posting at
|
||||
* PackedBlockSize+1<sup>th</sup>, 2*PackedBlockSize+1<sup>th</sup> ... , in DocFile.
|
||||
* The file offsets are relative to the start of current term's TermFreqs.
|
||||
* On disk it is also stored as the difference from previous SkipDatum in the sequence.</li>
|
||||
* <li>Since positions and payloads are also block encoded, the skip should skip to related block first,
|
||||
* then fetch the values according to in-block offset. PosFPSkip and PayFPSkip record the file
|
||||
* offsets of related block in .pos and .pay, respectively. While PosBlockOffset indicates
|
||||
* which value to fetch inside the related block (PayBlockOffset is unnecessary since it is always
|
||||
* equal to PosBlockOffset). Same as DocFPSkip, the file offsets are relative to the start of
|
||||
* current term's TermFreqs, and stored as a difference sequence.</li>
|
||||
* <li>PayLength indicates the length of last payload.</li>
|
||||
* <li>OffsetStart indicates the first value of last offset pair.</li>
|
||||
* </ul>
|
||||
* </dd>
|
||||
* </dl>
|
||||
*
|
||||
* <a name="Positions" id="Positions"></a>
|
||||
* <dl>
|
||||
* <dd>
|
||||
* <b>Positions</b>
|
||||
* <ul>
|
||||
* <li>Pos(.prx) --> Header, <TermPositions> <sup>TermCount</sup></li>
|
||||
* <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
|
||||
* <li>TermPositions --> < PackedPosDeltaBlock > <sup>PackedPosBlockNum</sup>,
|
||||
* VIntBlock? </li>
|
||||
* <li>VIntBlock --> PosVIntCount < PosDelta[, PayLength?], PayData?,
|
||||
* OffsetStartDelta?, OffsetLength? ><sup>PosVIntCount</sup>
|
||||
* <li>PackedPosDeltaBlock --> {@link PackedInts PackedInts}</li>
|
||||
* <li>PosVIntCount, PosDelta, OffsetStartDelta, OffsetLength -->
|
||||
* {@link DataOutput#writeVInt VInt}</li>
|
||||
* <li>PayData --> {@link DataOutput#writeByte byte}<sup>PayLength</sup></li>
|
||||
* </ul>
|
||||
* <p>Notes:</p>
|
||||
* <ul>
|
||||
* <li>TermPositions are order by term (terms are implicit, from the term dictionary), and position
|
||||
* values for each term document pair are incremental, and ordered by document number.</li>
|
||||
* <li>The procedure how PackedPosDeltaBlock is generated is the same as PackedDocDeltaBlock
|
||||
* in chapter <a href="#Frequencies">Frequencies and Skip Data</a>.</li>
|
||||
* <li>PosDelta is the same as the format mentioned in
|
||||
* <!--NOTE: change this manual html link, when directory structure is changed. -->
|
||||
* <a href="../../../../../org/apache/lucene/codecs/lucene40/Lucene40PostingsFormat.html#Positions">Lucene40PostingsFormat:Positions</a>
|
||||
* </li>
|
||||
* <li>OffsetStartDelta is the difference between this position's startOffset from the previous
|
||||
* occurrence (or zero, if this is the first occurrence in this document).</li>
|
||||
* <li>OffsetLength indicates the length of the current offset (endOffset-startOffset).</li>
|
||||
* <li>PayloadData is the blob of metadata associated with current position.</li>
|
||||
* </ul>
|
||||
* </dd>
|
||||
* </dl>
|
||||
*
|
||||
* <a name="Payloads" id="Payloads"></a>
|
||||
* <dl>
|
||||
* <dd>
|
||||
* <b>Payloads and Offsets</b>
|
||||
* <ul>
|
||||
* <li>PayFile(.pay): --> Header, <TermPayloads, TermOffsets?> <sup>TermCount</sup></li>
|
||||
* <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
|
||||
* <li>TermPayloads --> < PackedPayLengthBlock, PayBlockLength, PayData, PackedOffsetStartDeltaBlock?, PackedOffsetLengthBlock > <sup>PackedPayBlockNum</sup>
|
||||
* <li>PackedPayLengthBlock, PackedOffsetStartDeltaBlock, PackedOffsetLengthBlock --> {@link PackedInts PackedInts}</li>
|
||||
* <li>PayBlockLength --> {@link DataOutput#writeVInt VInt}</li>
|
||||
* <li>PayData --> {@link DataOutput#writeByte byte}<sup>PayBlockLength</sup></li>
|
||||
* </ul>
|
||||
* <p>Notes:</p>
|
||||
* <ul>
|
||||
* <li>The order of TermPayloads/TermOffsets will be the same as TermPositions, note that part of
|
||||
* payload/offsets are stored in .pos.</li>
|
||||
* <li>The procedure how PackedPayLengthBlock is generated is the same as PackedFreqBlock
|
||||
* in chapter <a href="#Frequencies">Frequencies and Skip Data</a>.</li>
|
||||
* <li>PayBlockLength is the total length of payloads written within one block, should be the sum
|
||||
* of PayLengths in one packed block.</li>
|
||||
* <li>PayLength is the length of each payload, associated with current position.</li>
|
||||
* </u>
|
||||
* </dd>
|
||||
* </dl>
|
||||
* </p>
|
||||
*
|
||||
*/
|
||||
|
||||
public final class BlockPostingsFormat extends PostingsFormat {
|
||||
public static final String DOC_EXTENSION = "doc";
|
||||
public static final String POS_EXTENSION = "pos";
|
||||
|
|
@ -42,7 +322,7 @@ public final class BlockPostingsFormat extends PostingsFormat {
|
|||
private final int minTermBlockSize;
|
||||
private final int maxTermBlockSize;
|
||||
|
||||
// NOTE: must be factor of 64 because of PackedInts long-aligned encoding/decoding
|
||||
// NOTE: must be multiple of 64 because of PackedInts long-aligned encoding/decoding
|
||||
public final static int BLOCK_SIZE = 128;
|
||||
|
||||
public BlockPostingsFormat() {
|
||||
|
|
|
|||
|
|
@ -52,7 +52,7 @@ import org.apache.lucene.util.IOUtils;
|
|||
* @see BlockSkipReader for details
|
||||
*
|
||||
*/
|
||||
public final class BlockPostingsReader extends PostingsReaderBase {
|
||||
final class BlockPostingsReader extends PostingsReaderBase {
|
||||
|
||||
private final IndexInput docIn;
|
||||
private final IndexInput posIn;
|
||||
|
|
|
|||
|
|
@ -159,7 +159,7 @@ import org.apache.lucene.util.fst.FST; // javadocs
|
|||
* with the frequency of the term in that document (except when frequencies are
|
||||
* omitted: {@link IndexOptions#DOCS_ONLY}).</p>
|
||||
* <ul>
|
||||
* <li>FreqFile (.frq) --> Header, <TermFreqs, SkipData> <sup>TermCount</sup></li>
|
||||
* <li>FreqFile (.frq) --> Header, <TermFreqs, SkipData?> <sup>TermCount</sup></li>
|
||||
* <li>Header --> {@link CodecUtil#writeHeader CodecHeader}</li>
|
||||
* <li>TermFreqs --> <TermFreq> <sup>DocFreq</sup></li>
|
||||
* <li>TermFreq --> DocDelta[, Freq?]</li>
|
||||
|
|
|
|||
Loading…
Reference in New Issue