You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ka...@apache.org on 2026/08/06 17:59:16 UTC
(lucene) branch main updated (640e7dc4910 -> 4a3ed979145)
This is an automated email from the ASF dual-hosted git repository.
kaivalnp pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/lucene.git
from 640e7dc4910 deps(java): bump com.github.luben:zstd-jni from 1.5.7-11 to 1.5.7-12 (#16486)
add 4a3ed979145 Add a sandboxed de-duplicating HNSW vector format (#15979)
No new revisions were added by this update.
Summary of changes:
lucene/CHANGES.txt | 4 +
.../codecs/lucene99/Lucene99HnswVectorsReader.java | 4 +
.../codecs/lucene99/Lucene99HnswVectorsWriter.java | 14 +-
lucene/sandbox/src/java/module-info.java | 4 +-
.../codecs/dedup/DedupFlatFieldVectorsWriter.java | 110 +++++
.../codecs/dedup/DedupFlatVectorsFormat.java | 137 ++++++
.../codecs/dedup/DedupFlatVectorsReader.java | 361 ++++++++++++++
.../codecs/dedup/DedupFlatVectorsScorer.java | 187 ++++++++
.../codecs/dedup/DedupFlatVectorsWriter.java | 155 ++++++
.../sandbox/codecs/dedup/DedupFlushContext.java | 306 ++++++++++++
.../lucene/sandbox/codecs/dedup/DedupGroup.java | 105 +++++
.../codecs/dedup/DedupHnswVectorsFormat.java} | 127 ++---
.../sandbox/codecs/dedup/DedupMergeContext.java | 417 +++++++++++++++++
.../lucene/sandbox/codecs/dedup/DedupUtil.java | 193 ++++++++
.../sandbox/codecs/dedup/DedupVectorValues.java | 519 +++++++++++++++++++++
.../lucene/sandbox/codecs/dedup}/package-info.java | 9 +-
.../org.apache.lucene.codecs.KnnVectorsFormat | 1 +
.../codecs/dedup/TestDedupFlatVectorsFormat.java | 440 +++++++++++++++++
.../codecs/dedup/TestDedupHnswVectorsFormat.java | 255 ++++++++++
.../tests/index/BaseKnnVectorsFormatTestCase.java | 5 +-
20 files changed, 3283 insertions(+), 70 deletions(-)
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupFlatFieldVectorsWriter.java
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupFlatVectorsFormat.java
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupFlatVectorsReader.java
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupFlatVectorsScorer.java
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupFlatVectorsWriter.java
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupFlushContext.java
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupGroup.java
copy lucene/{core/src/java/org/apache/lucene/codecs/lucene104/Lucene104HnswScalarQuantizedVectorsFormat.java => sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupHnswVectorsFormat.java} (61%)
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupMergeContext.java
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupUtil.java
create mode 100644 lucene/sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup/DedupVectorValues.java
copy lucene/{analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/hhmm => sandbox/src/java/org/apache/lucene/sandbox/codecs/dedup}/package-info.java (65%)
create mode 100644 lucene/sandbox/src/test/org/apache/lucene/sandbox/codecs/dedup/TestDedupFlatVectorsFormat.java
create mode 100644 lucene/sandbox/src/test/org/apache/lucene/sandbox/codecs/dedup/TestDedupHnswVectorsFormat.java