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

Skip decoding tail freqs when they are not needed. (#12832) 

When we moved to group-varint for tail postings, we stop interleaving docs and
freqs and instead wrote all docs first, then all freqs. This means that we can
now skip decoding frequencies when they are not needed.
This commit is contained in:
Adrien Grand 2023-11-22 10:05:41 +01:00 committed by GitHub
parent 4628327af0
commit 5bc608dbad
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 16 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
lucene/core/src/java/org/apache/lucene/codecs/lucene99/Lucene99PostingsReader.java
View File

@ -142,10 +142,15 @@ public final class Lucene99PostingsReader extends PostingsReaderBase {
/** Read values that have been written using variable-length encoding instead of bit-packing. */
static void readVIntBlock(
IndexInput docIn, long[] docBuffer, long[] freqBuffer, int num, boolean indexHasFreq)
IndexInput docIn,
long[] docBuffer,
long[] freqBuffer,
int num,
boolean indexHasFreq,
boolean decodeFreq)
throws IOException {
GroupVIntReader.readValues(docIn, docBuffer, num);
if (indexHasFreq) {
if (indexHasFreq && decodeFreq) {
for (int i = 0; i < num; ++i) {
freqBuffer[i] = docBuffer[i] & 0x01;
docBuffer[i] >>= 1;
@ -153,6 +158,10 @@ public final class Lucene99PostingsReader extends PostingsReaderBase {
freqBuffer[i] = docIn.readVInt();
}
}
} else if (indexHasFreq) {
for (int i = 0; i < num; ++i) {
docBuffer[i] >>= 1;
}
}
}
@ -466,7 +475,7 @@ public final class Lucene99PostingsReader extends PostingsReaderBase {
blockUpto++;
} else {
// Read vInts:
readVIntBlock(docIn, docBuffer, freqBuffer, left, indexHasFreq);
readVIntBlock(docIn, docBuffer, freqBuffer, left, indexHasFreq, needsFreq);
prefixSum(docBuffer, left, accum);
docBuffer[left] = NO_MORE_DOCS;
blockUpto += left;
@ -759,7 +768,7 @@ public final class Lucene99PostingsReader extends PostingsReaderBase {
docBuffer[1] = NO_MORE_DOCS;
blockUpto++;
} else {
readVIntBlock(docIn, docBuffer, freqBuffer, left, true);
readVIntBlock(docIn, docBuffer, freqBuffer, left, true, true);
prefixSum(docBuffer, left, accum);
docBuffer[left] = NO_MORE_DOCS;
blockUpto += left;
@ -1146,7 +1155,7 @@ public final class Lucene99PostingsReader extends PostingsReaderBase {
}
blockUpto += BLOCK_SIZE;
} else {
readVIntBlock(docIn, docBuffer, freqBuffer, left, indexHasFreqs);
readVIntBlock(docIn, docBuffer, freqBuffer, left, indexHasFreqs, true);
prefixSum(docBuffer, left, accum);
docBuffer[left] = NO_MORE_DOCS;
blockUpto += left;
@ -1354,7 +1363,7 @@ public final class Lucene99PostingsReader extends PostingsReaderBase {
forDeltaUtil.decodeAndPrefixSum(docIn, accum, docBuffer);
pforUtil.decode(docIn, freqBuffer);
} else {
readVIntBlock(docIn, docBuffer, freqBuffer, left, true);
readVIntBlock(docIn, docBuffer, freqBuffer, left, true, true);
prefixSum(docBuffer, left, accum);
docBuffer[left] = NO_MORE_DOCS;
}
@ -1744,7 +1753,7 @@ public final class Lucene99PostingsReader extends PostingsReaderBase {
false; // freq block will be loaded lazily when necessary, we don't load it here
}
} else {
readVIntBlock(docIn, docBuffer, freqBuffer, left, indexHasFreq);
readVIntBlock(docIn, docBuffer, freqBuffer, left, indexHasFreq, true);
prefixSum(docBuffer, left, accum);
docBuffer[left] = NO_MORE_DOCS;
}