Implement advanced primer search filtering and reference handling

This update introduces new configuration options for pair selection, including multi-match filtering, circularity settings, and reference site validation. It also enhances the search functionality to correctly identify and track repeated sequences and reference locations, improving the accuracy of primer pair identification.

pkg/obiprimer/reference.go

@@ -0,0 +1,44 @@
+package obiprimer
+
+import (
+	"fmt"
+	"strings"
+
+	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiseq"
+)
+
+// span writes the 1-based GenBank range of the lp bases starting at the 0-based
+// position pos. On a circular sequence a range running over the junction is
+// split in two.
+func span(pos, lp, n int, circular bool) string {
+	end := pos + lp
+	if end > n && circular {
+		return fmt.Sprintf("%d..%d,1..%d", pos+1, n, end-n)
+	}
+	return fmt.Sprintf("%d..%d", pos+1, end)
+}
+
+// referenceSites describes an amplicon of a pair on the reference sequence raw.
+//
+// The location lists the two primer sites left to right as join(a..b,c..d),
+// inside complement() when the first primer of the pair (Primer1 once the pair
+// is in string order) binds the reverse strand. The amplicon is the region
+// between the sites, read 5'->3' from the first primer, in lower case.
+//
+// swappedByOrder says whether putting the pair in string order exchanged the
+// two primers of the key.
+func referenceSites(raw []byte, h refHit, p PairParams, swappedByOrder bool) (location, amplicon string) {
+	lp, n := p.PrimerLength, len(raw)
+
+	// The key slot 1 is the upstream primer unless the match order was swapped;
+	// the exchange due to the string order flips it again.
+	firstIsUpstream := h.swapped == swappedByOrder
+
+	location = "join(" + span(int(h.up.pos), lp, n, p.Circular) + "," + span(int(h.down.pos), lp, n, p.Circular) + ")"
+	region := []byte(strings.ToLower(string(raw[int(h.up.pos)+lp : int(h.down.pos)])))
+	if firstIsUpstream {
+		return location, string(region)
+	}
+	rc := obiseq.NewBioSequence("", region, "").ReverseComplement(true)
+	return "complement(" + location + ")", string(rc.Sequence())
+}