Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-4497: don't write PosVIntCount in 4.1 codec 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1400974 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2012-10-22 17:55:39 +00:00
parent 733654068a
commit 4a17b6a1ed
4 changed files with 11 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lucene/CHANGES.txt
View File

@ -105,6 +105,9 @@ Optimizations
the postings data (via flags to TermsEnum.docs/docsAndPositions) to use
ForUtil.skipBlock. (Robert Muir)
* LUCENE-4497: Don't write PosVIntCount to the positions file in
Lucene41PostingsFormat, as its always totalTermFreq % BLOCK_SIZE. (Robert Muir)
Build
* LUCENE-4451: Memory leak per unique thread caused by

2
lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsFormat.java
View File

@ -274,7 +274,7 @@ import org.apache.lucene.util.packed.PackedInts;
* <li>Header --&gt; {@link CodecUtil#writeHeader CodecHeader}</li>
* <li>TermPositions --&gt; &lt;PackedPosDeltaBlock&gt; <sup>PackedPosBlockNum</sup>,
* VIntBlock? </li>
* <li>VIntBlock --&gt; PosVIntCount, &lt;PositionDelta[, PayloadLength?], PayloadData?,
* <li>VIntBlock --&gt; &lt;PositionDelta[, PayloadLength?], PayloadData?,
* OffsetDelta?, OffsetLength?&gt;<sup>PosVIntCount</sup>
* <li>PackedPosDeltaBlock --&gt; {@link PackedInts PackedInts}</li>
* <li>PosVIntCount, PositionDelta, OffsetDelta, OffsetLength --&gt;

8
lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsReader.java
View File

@ -597,6 +597,7 @@ public final class Lucene41PostingsReader extends PostingsReaderBase {
final boolean indexHasPayloads;
private int docFreq; // number of docs in this posting list
private long totalTermFreq; // number of positions in this posting list
private int docUpto; // how many docs we've read
private int doc; // doc we last read
private int accum; // accumulator for doc deltas
@ -661,6 +662,7 @@ public final class Lucene41PostingsReader extends PostingsReaderBase {
payTermStartFP = termState.payStartFP;
docIn.seek(docTermStartFP);
skipOffset = termState.skipOffset;
totalTermFreq = termState.totalTermFreq;
posPendingFP = posTermStartFP;
posPendingCount = 0;
if (termState.totalTermFreq < BLOCK_SIZE) {
@ -721,7 +723,7 @@ public final class Lucene41PostingsReader extends PostingsReaderBase {
// if (DEBUG) {
// System.out.println(" vInt pos block @ fp=" + posIn.getFilePointer() + " hasPayloads=" + indexHasPayloads + " hasOffsets=" + indexHasOffsets);
// }
final int count = posIn.readVInt();
final int count = (int) (totalTermFreq % BLOCK_SIZE);
int payloadLength = 0;
for(int i=0;i<count;i++) {
int code = posIn.readVInt();
@ -1009,6 +1011,7 @@ public final class Lucene41PostingsReader extends PostingsReaderBase {
final boolean indexHasPayloads;
private int docFreq; // number of docs in this posting list
private long totalTermFreq; // number of positions in this posting list
private int docUpto; // how many docs we've read
private int doc; // doc we last read
private int accum; // accumulator for doc deltas
@ -1100,6 +1103,7 @@ public final class Lucene41PostingsReader extends PostingsReaderBase {
payTermStartFP = termState.payStartFP;
docIn.seek(docTermStartFP);
skipOffset = termState.skipOffset;
totalTermFreq = termState.totalTermFreq;
posPendingFP = posTermStartFP;
payPendingFP = payTermStartFP;
posPendingCount = 0;
@ -1163,7 +1167,7 @@ public final class Lucene41PostingsReader extends PostingsReaderBase {
// if (DEBUG) {
// System.out.println(" vInt pos block @ fp=" + posIn.getFilePointer() + " hasPayloads=" + indexHasPayloads + " hasOffsets=" + indexHasOffsets);
// }
final int count = posIn.readVInt();
final int count = (int) (totalTermFreq % BLOCK_SIZE);
int payloadLength = 0;
int offsetLength = 0;
payloadByteUpto = 0;

4
lucene/core/src/java/org/apache/lucene/codecs/lucene41/Lucene41PostingsWriter.java
View File

@ -417,9 +417,7 @@ public final class Lucene41PostingsWriter extends PostingsWriterBase {
} else {
lastPosBlockOffset = -1;
}
if (posBufferUpto > 0) {
posOut.writeVInt(posBufferUpto);
if (posBufferUpto > 0) {
// TODO: should we send offsets/payloads to
// .pay...? seems wasteful (have to store extra
// vLong for low (< BLOCK_SIZE) DF terms = vast vast