Extract dereplication logic into obikderep crate and centralize paths
Move partition dereplication logic into a dedicated `obikderep` crate that implements a two-phase hash-split/merge strategy with Rayon for parallel processing. Centralize superkmer file path construction in `obilayeredmap` and update dependent crates to use the new pipeline and shared path helpers. Adjust test suites to explicitly invoke the dereplication step.
This commit is contained in:
@@ -20,6 +20,7 @@ rayon = "1"
|
||||
tracing = "0.1.44"
|
||||
|
||||
[dev-dependencies]
|
||||
obiread = { path = "../obiread" }
|
||||
obiread = { path = "../obiread" }
|
||||
obikderep = { path = "../obikderep" }
|
||||
tempfile = "3"
|
||||
tracing-subscriber = { version = "0.3", features = ["fmt", "env-filter"] }
|
||||
|
||||
@@ -6,6 +6,7 @@ use obilayeredmap::MphfLayer;
|
||||
use obisys::Reporter;
|
||||
use tempfile::tempdir;
|
||||
|
||||
use obikderep::Dereplicator;
|
||||
use obikindex::{GenomeInfo, IndexConfig, KmerIndex, MergeMode};
|
||||
use obikpartitionner::PartitionRouter;
|
||||
|
||||
@@ -76,7 +77,10 @@ fn build_single_genome_index(dir: &Path, label: &str, seq: &[u8]) -> KmerIndex {
|
||||
router.write_batch(batch).expect("write_batch");
|
||||
}
|
||||
router.close().expect("close partition writers");
|
||||
router.dereplicate().expect("dereplicate");
|
||||
drop(router); // ends the borrow of `idx` early — `PartitionRouter`'s `Drop` impl would otherwise extend it to the end of scope
|
||||
|
||||
Dereplicator::new(&idx).run(None::<fn(obisys::Progress)>).expect("dereplicate");
|
||||
let router = PartitionRouter::new(&mut idx);
|
||||
let spectrum = router.count_kmer(false).expect("count_kmer");
|
||||
drop(router); // ends the borrow of `idx` early — `PartitionRouter`'s `Drop` impl would otherwise extend it to the end of scope
|
||||
|
||||
|
||||
Reference in New Issue
Block a user