Refactor k-mer index management with subcommands and enhanced metadata support

This commit refactors the k-mer index management tools to use a unified subcommand structure with obik, adds support for per-set metadata and ID management, enhances the k-mer set group builder to support appending to existing groups, and improves command-line option handling with a new global options registration system.

Key changes:
- Introduce obik command with subcommands (index, ls, summary, cp, mv, rm, super, lowmask)
- Add support for per-set metadata and ID management in kmer set groups
- Implement ability to append to existing kmer index groups
- Refactor option parsing to use a global options registration system
- Add new commands for listing, copying, moving, and removing sets
- Enhance low-complexity masking with new options and output formats
- Improve kmer index summary with Jaccard distance matrix support
- Remove deprecated obikindex and obisuperkmer commands
- Update build process to use the new subcommand structure
This commit is contained in:
Eric Coissac
2026-02-09 23:10:30 +01:00
parent f78543ee75
commit 56c1f4180c
26 changed files with 1482 additions and 1175 deletions

34
cmd/obitools/obik/main.go Normal file
View File

@@ -0,0 +1,34 @@
package main
import (
"context"
"errors"
"os"
log "github.com/sirupsen/logrus"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obioptions"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiseq"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitools/obik"
"github.com/DavidGamba/go-getoptions"
)
func main() {
defer obiseq.LogBioSeqStatus()
opt, parser := obioptions.GenerateSubcommandParser(
"obik",
"Manage disk-based kmer indices",
obik.OptionSet,
)
_, remaining := parser(os.Args)
err := opt.Dispatch(context.Background(), remaining)
if err != nil {
if errors.Is(err, getoptions.ErrorHelpCalled) {
os.Exit(0)
}
log.Fatalf("Error: %v", err)
}
}

View File

@@ -1,23 +0,0 @@
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 disk-based kmer index from sequence files",
obikindex.OptionSet)
_, args := optionParser(os.Args)
sequences, err := obiconvert.CLIReadBioSequences(args...)
obiconvert.OpenSequenceDataErrorMessage(args, err)
obikindex.CLIBuildKmerIndex(sequences)
}

View File

@@ -1,47 +0,0 @@
package main
import (
"os"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obioptions"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiseq"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitools/obiconvert"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitools/obilowmask"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiutils"
)
func main() {
defer obiseq.LogBioSeqStatus()
// go tool pprof -http=":8000" ./obipairing ./cpu.pprof
// f, err := os.Create("cpu.pprof")
// if err != nil {
// log.Fatal(err)
// }
// pprof.StartCPUProfile(f)
// defer pprof.StopCPUProfile()
// go tool trace cpu.trace
// ftrace, err := os.Create("cpu.trace")
// if err != nil {
// log.Fatal(err)
// }
// trace.Start(ftrace)
// defer trace.Stop()
optionParser := obioptions.GenerateOptionParser(
"obimicrosat",
"looks for microsatellites sequences in a sequence file",
obilowmask.OptionSet)
_, args := optionParser(os.Args)
sequences, err := obiconvert.CLIReadBioSequences(args...)
obiconvert.OpenSequenceDataErrorMessage(args, err)
selected := obilowmask.CLISequenceEntropyMasker(sequences)
obiconvert.CLIWriteBioSequences(selected, true)
obiutils.WaitForLastPipe()
}

View File

@@ -1,34 +0,0 @@
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/obisuperkmer"
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiutils"
)
func main() {
// Generate option parser
optionParser := obioptions.GenerateOptionParser(
"obisuperkmer",
"extract super k-mers from sequence files",
obisuperkmer.OptionSet)
// Parse command-line arguments
_, args := optionParser(os.Args)
// Read input sequences
sequences, err := obiconvert.CLIReadBioSequences(args...)
obiconvert.OpenSequenceDataErrorMessage(args, err)
// Extract super k-mers
superkmers := obisuperkmer.CLIExtractSuperKmers(sequences)
// Write output sequences
obiconvert.CLIWriteBioSequences(superkmers, true)
// Wait for pipeline completion
obiutils.WaitForLastPipe()
}