Implement proximityPrecision setting on milli side

This commit is contained in:
ManyTheFish
2023-12-06 15:49:02 +01:00
parent 0c3fa8cbc4
commit 467b49153d
6 changed files with 224 additions and 66 deletions

View File

@ -32,6 +32,7 @@ use super::helpers::{
MergeFn, MergeableReader,
};
use super::{helpers, TypedChunk};
use crate::proximity::ProximityPrecision;
use crate::{FieldId, Result};
/// Extract data for each databases from obkv documents in parallel.
@ -52,7 +53,7 @@ pub(crate) fn data_from_obkv_documents(
dictionary: Option<&[&str]>,
max_positions_per_attributes: Option<u32>,
exact_attributes: HashSet<FieldId>,
// TODO: add a proximity database deactivation parameter.
proximity_precision: ProximityPrecision,
) -> Result<()> {
puffin::profile_function!();
@ -151,16 +152,17 @@ pub(crate) fn data_from_obkv_documents(
});
}
// TODO: Skip this part if deactivated
spawn_extraction_task::<_, _, Vec<grenad::Reader<BufReader<File>>>>(
docid_word_positions_chunks.clone(),
indexer,
lmdb_writer_sx.clone(),
extract_word_pair_proximity_docids,
merge_deladd_cbo_roaring_bitmaps,
TypedChunk::WordPairProximityDocids,
"word-pair-proximity-docids",
);
if proximity_precision == ProximityPrecision::WordScale {
spawn_extraction_task::<_, _, Vec<grenad::Reader<BufReader<File>>>>(
docid_word_positions_chunks.clone(),
indexer,
lmdb_writer_sx.clone(),
extract_word_pair_proximity_docids,
merge_deladd_cbo_roaring_bitmaps,
TypedChunk::WordPairProximityDocids,
"word-pair-proximity-docids",
);
}
spawn_extraction_task::<_, _, Vec<grenad::Reader<BufReader<File>>>>(
docid_word_positions_chunks.clone(),

View File

@ -352,6 +352,7 @@ where
let dictionary: Option<Vec<_>> =
dictionary.as_ref().map(|x| x.iter().map(String::as_str).collect());
let exact_attributes = self.index.exact_attributes_ids(self.wtxn)?;
let proximity_precision = self.index.proximity_precision(self.wtxn)?.unwrap_or_default();
let pool_params = GrenadParameters {
chunk_compression_type: self.indexer_config.chunk_compression_type,
@ -392,6 +393,7 @@ where
dictionary.as_deref(),
max_positions_per_attributes,
exact_attributes,
proximity_precision,
)
});