mirror of
https://github.com/metabarcoding/obitools4.git
synced 2026-03-25 13:30:52 +00:00
Refactor kmer index to disk-based partitioning with minimizer
Refactor kmer index package to use disk-based partitioning with minimizer - Replace roaring64 bitmaps with disk-based kmer index - Implement partitioned kmer sets with delta-varint encoding - Add support for frequency filtering during construction - Introduce new builder pattern for index construction - Add streaming operations for set operations (union, intersect, etc.) - Add support for super-kmer encoding during construction - Update command line tool to use new index format - Remove dependency on roaring bitmap library This change introduces a new architecture for kmer indexing that is more memory efficient and scalable for large datasets.
This commit is contained in:
23
cmd/obitools/obikindex/main.go
Normal file
23
cmd/obitools/obikindex/main.go
Normal file
@@ -0,0 +1,23 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"os"
|
||||
|
||||
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obioptions"
|
||||
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitools/obiconvert"
|
||||
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitools/obikindex"
|
||||
)
|
||||
|
||||
func main() {
|
||||
optionParser := obioptions.GenerateOptionParser(
|
||||
"obikindex",
|
||||
"builds a roaring kmer index from sequence files",
|
||||
obikindex.OptionSet)
|
||||
|
||||
_, args := optionParser(os.Args)
|
||||
|
||||
sequences, err := obiconvert.CLIReadBioSequences(args...)
|
||||
obiconvert.OpenSequenceDataErrorMessage(args, err)
|
||||
|
||||
obikindex.CLIBuildKmerIndex(sequences)
|
||||
}
|
||||
Reference in New Issue
Block a user