mirror of
https://github.com/metabarcoding/obitools4.git
synced 2026-11-09 17:24:41 +00:00
Eric Coissac
e511650f5b
Introduces parallel processing for clustering, refines scoring mechanisms, and expands test coverage for the alignment functionality. This change introduces parallel processing capabilities within the clustering logic, updates the core similarity engine with new data structures and scoring methods, and implements a comprehensive test suite for the alignment tool. It also adds new command-line options for configuring alignment parameters and reference lengths.
39 lines
1009 B
Go
39 lines
1009 B
Go
package obiformats
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
"testing"
|
|
)
|
|
|
|
// With a single reader, the sequences of several files must come out in the
|
|
// order of the files, whatever the order in which the batches are parsed.
|
|
func TestReadSequencesBatchFromFilesKeepsOrder(t *testing.T) {
|
|
dir := t.TempDir()
|
|
var names []string
|
|
for _, prefix := range []string{"a", "b"} {
|
|
var sb strings.Builder
|
|
for i := 0; i < 25000; i++ {
|
|
fmt.Fprintf(&sb, ">%s%07d {\"k\":%d}\n%s\n", prefix, i, i, strings.Repeat("acgt", 40))
|
|
}
|
|
name := filepath.Join(dir, prefix+".fasta")
|
|
if err := os.WriteFile(name, []byte(sb.String()), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
names = append(names, name)
|
|
}
|
|
|
|
it := ReadSequencesBatchFromFiles(names, nil, 1)
|
|
_, db := it.Load()
|
|
if len(db) != 50000 {
|
|
t.Fatalf("expected 50000 sequences, got %d", len(db))
|
|
}
|
|
for i := 1; i < len(db); i++ {
|
|
if db[i-1].Id() >= db[i].Id() {
|
|
t.Fatalf("out of order at %d: %s then %s", i, db[i-1].Id(), db[i].Id())
|
|
}
|
|
}
|
|
}
|