Merge pull request #113 from metabarcoding/push-oxowomxlnlnx

Push oxowomxlnlnx

pkg/obioptions/version.go

@@ -3,7 +3,7 @@ package obioptions
 // Version is automatically updated by the Makefile from version.txt
 // The patch number (third digit) is incremented on each push to the repository
 
-var _Version = "Release 4.4.40"
+var _Version = "Release 4.4.41"
 
 // Version returns the version of the obitools package.
 //

pkg/obiseq/biosequence.go

@@ -499,6 +499,9 @@ func (s *BioSequence) SetQualities(qualities Quality) {
 	if s.qualities != nil {
 		RecycleSlice(&s.qualities)
 	}
+	if len(qualities) > 0 && len(qualities) != len(s.sequence) {
+		log.Panicf("[BioSequence.SetQualities] Sequence %s has a length of %d and qualities a length of %d", s.id, len(s.sequence), len(qualities))
+	}
 	s.qualities = CopySlice(qualities)
 }
 
@@ -508,6 +511,9 @@ func (s *BioSequence) TakeQualities(qualities Quality) {
 	if s.qualities != nil {
 		RecycleSlice(&s.qualities)
 	}
+	if len(qualities) > 0 && len(qualities) != len(s.sequence) {
+		log.Panicf("[BioSequence.TakeQualities] Sequence %s has a length of %d and qualities a length of %d", s.id, len(s.sequence), len(qualities))
+	}
 	s.qualities = qualities
 }
 

pkg/obiseq/revcomp.go

@@ -118,6 +118,9 @@ func (sequence *BioSequence) _revcmpMutation() *BioSequence {
  */
 func ReverseComplementWorker(inplace bool) SeqWorker {
 	f := func(input *BioSequence) (BioSequenceSlice, error) {
+		if input.IsPaired() {
+			input.PairedWith().ReverseComplement(inplace)
+		}
 		return BioSequenceSlice{input.ReverseComplement(inplace)}, nil
 	}
 

pkg/obiseq/subseq.go

@@ -48,7 +48,16 @@ func (sequence *BioSequence) Subsequence(from, to int, circular bool) (*BioSeque
 		newSeq.sequence = CopySlice(sequence.Sequence()[from:to])
 
 		if sequence.HasQualities() {
-			newSeq.qualities = CopySlice(sequence.Qualities()[from:to])
+			qual := sequence.Qualities()
+			if len(qual) != sequence.Len() {
+				log.Panicf(
+					"[BioSequence.Subsequence] Sequence %s has a length of %d and qualities a length of %d",
+					sequence.Id(),
+					sequence.Len(),
+					len(qual),
+				)
+			}
+			newSeq.qualities = CopySlice(qual[from:to])
 		}
 
 		newSeq.id = fmt.Sprintf("%s_sub[%d..%d]", sequence.Id(), from+1, to)
@@ -58,7 +67,16 @@ func (sequence *BioSequence) Subsequence(from, to int, circular bool) (*BioSeque
 		newSeq.Write(sequence.Sequence()[0:to])
 
 		if sequence.HasQualities() {
-			newSeq.WriteQualities(sequence.Qualities()[0:to])
+			qual := sequence.Qualities()
+			if len(qual) != sequence.Len() {
+				log.Panicf(
+					"[BioSequence.Subsequence] Sequence %s has a length of %d and qualities a length of %d",
+					sequence.Id(),
+					sequence.Len(),
+					len(qual),
+				)
+			}
+			newSeq.WriteQualities(qual[0:to])
 		}
 
 	}

pkg/obitools/obicsv/obicsv.go

@@ -33,6 +33,7 @@ func CLIWriteSequenceCSV(iterator obiiter.IBioSequence,
 		CSVSequence(CLIPrintSequence()),
 		CSVQuality(CLIPrintQuality()),
 		CSVAutoColumn(CLIAutoColumns()),
+		CSVNAValue(CLINAValue()),
 	)
 
 	csvIter := NewCSVSequenceIterator(iterator, opts...)

pkg/obitools/obicsv/sequence.go

@@ -1,6 +1,7 @@
 package obicsv
 
 import (
+	"fmt"
 	"log"
 	"slices"
 
@@ -67,8 +68,19 @@ func CSVBatchFromSequences(batch obiiter.BioSequenceBatch, opt Options) obiiterc
 
 			if taxon != nil {
 				taxid = taxon.String()
+			} else if ta, ok := sequence.GetAttribute("taxid"); ok {
+				switch tv := ta.(type) {
+				case string:
+					taxid = tv
+				case int:
+					taxid = fmt.Sprintf("%d", tv)
+				case float64:
+					taxid = fmt.Sprintf("%d", int(tv))
+				default:
+					taxid = opt.CSVNAValue()
+				}
 			} else {
-				taxid = sequence.Taxid()
+				taxid = opt.CSVNAValue()
 			}
 
 			record["taxid"] = taxid

pkg/obitools/obisummary/obisummary.go

@@ -99,6 +99,17 @@ func (data1 *DataSummary) Add(data2 *DataSummary) *DataSummary {
 	rep.sample_singletons = sumUpdateIntMap(data1.sample_singletons, data2.sample_singletons)
 	rep.sample_obiclean_bad = sumUpdateIntMap(data1.sample_obiclean_bad, data2.sample_obiclean_bad)
 
+	for k, m1 := range data1.map_summaries {
+		rep.map_summaries[k] = m1
+	}
+	for k, m2 := range data2.map_summaries {
+		if m1, ok := rep.map_summaries[k]; ok {
+			rep.map_summaries[k] = sumUpdateIntMap(m1, m2)
+		} else {
+			rep.map_summaries[k] = m2
+		}
+	}
+
 	return rep
 }
 
@@ -163,8 +174,9 @@ func ISummary(iterator obiiter.IBioSequence, summarise []string) map[string]inte
 	summaries := make([]*DataSummary, nproc)
 
 	for n := 0; n < nproc; n++ {
+		summaries[n] = NewDataSummary()
 		for _, v := range summarise {
-			summaries[n].map_summaries[v] = make(map[string]int, 0)
+			summaries[n].map_summaries[v] = make(map[string]int)
 		}
 	}
 
@@ -174,6 +186,11 @@ func ISummary(iterator obiiter.IBioSequence, summarise []string) map[string]inte
 			batch := iseq.Get()
 			for _, seq := range batch.Slice() {
 				summary.Update(seq)
+				for _, attr := range summarise {
+					if m, ok := seq.GetIntMap(attr); ok {
+						summary.map_summaries[attr] = sumUpdateIntMap(summary.map_summaries[attr], m)
+					}
+				}
 			}
 		}
 		waiter.Done()
@@ -181,11 +198,9 @@ func ISummary(iterator obiiter.IBioSequence, summarise []string) map[string]inte
 
 	waiter.Add(nproc)
 
-	summaries[0] = NewDataSummary()
 	go ff(iterator, summaries[0])
 
 	for i := 1; i < nproc; i++ {
-		summaries[i] = NewDataSummary()
 		go ff(iterator.Split(), summaries[i])
 	}
 
@@ -246,5 +261,14 @@ func ISummary(iterator obiiter.IBioSequence, summarise []string) map[string]inte
 			}
 		}
 	}
+
+	if len(rep.map_summaries) > 0 {
+		mapDict := make(map[string]interface{}, len(rep.map_summaries))
+		for attr, counts := range rep.map_summaries {
+			mapDict[attr] = counts
+		}
+		dict["map_summaries"] = mapDict
+	}
+
 	return dict
 }

version.txt

@@ -1 +1 @@
-4.4.40
+4.4.41