Merge pull request #122 from metabarcoding/push-tnmnuwllvnop

Release 4.5.0

Makefile

@@ -156,8 +156,8 @@ bump-version:
 
 jjnew:
 	@echo "$(YELLOW)→ Creating a new commit...$(NC)"
-	@echo "$(BLUE)→ Documenting current commit...$(NC)"
-	@jj auto-describe
+	@echo "$(BLUE)→ Documenting undocumented commits...$(NC)"
+	@jj auto-doc
 	@echo "$(BLUE)→ Done.$(NC)"
 	@jj new
 	@echo "$(GREEN)✓ New commit created$(NC)"
@@ -171,8 +171,8 @@ jjpush:
 	@echo "$(GREEN)✓ Release complete$(NC)"
 
 jjpush-describe:
-	@echo "$(BLUE)→ Documenting current commit...$(NC)"
-	@jj auto-describe
+	@echo "$(BLUE)→ Documenting undocumented commits...$(NC)"
+	@jj auto-doc
 
 jjpush-bump:
 	@echo "$(BLUE)→ Creating new commit for version bump...$(NC)"

pkg/obialign/locatepattern.go

@@ -28,10 +28,18 @@ func buffIndex(i, j, width int) int {
 //
 // The function returns the start and end positions of the best
 // match, as well as the number of errors in the best match.
+//
+// When the sequence is too short relative to the pattern for the
+// backtracking to reconstruct a valid alignment (e.g. the pattern
+// is longer than the sequence, or the match sits too close to a
+// sequence boundary), no reliable position can be computed. In that
+// case the function returns the sentinel (-1, -1, -1) instead of a
+// guessed, potentially wrong, position: callers must treat this as
+// "no match" rather than use the returned coordinates.
 func LocatePattern(id string, pattern, sequence []byte) (int, int, int) {
 
-	if len(pattern) >= len(sequence) {
-		log.Panicf("Sequence %s:Pattern %s must be shorter than sequence %s", id, pattern, sequence)
+	if len(sequence) == 0 {
+		log.Panicf("Sequence %s:Pattern %s must not be empty", id, pattern)
 	}
 
 	// Pattern spreads over the columns
@@ -158,5 +166,18 @@ func LocatePattern(id string, pattern, sequence []byte) (int, int, int) {
 	// obilog.Warnf("from : %d to: %d error: %d match: %v",
 	// 	i, end+1, -buffer[buffIndex(len(sequence)-1, len(pattern)-1, width)],
 	// 	string(sequence[i:(end+1)]))
+
+	if i < 0 || end == -1 {
+		// i < 0: the backtracking ran off the start of the sequence
+		// without fully consuming the pattern.
+		// end == -1: the backtracking loop never ran at all (e.g. a
+		// single-base pattern, jmax == 0), so no alignment boundary
+		// was ever established.
+		// Either way, no valid alignment exists for this (pattern,
+		// sequence) pair: signal it explicitly instead of returning
+		// an out-of-bounds or uncomputed position.
+		return -1, -1, -1
+	}
+
 	return i, end + 1, -buffer[buffIndex(len(sequence)-1, len(pattern)-1, width)]
 }

pkg/obialign/locatepattern_test.go

@@ -0,0 +1,123 @@
+package obialign
+
+import (
+	"math/rand"
+	"testing"
+)
+
+func TestLocatePatternNormal(t *testing.T) {
+	// Pattern fully and exactly present in the middle of a longer sequence.
+	start, end, nerr := LocatePattern("id", []byte("ACGT"), []byte("TTTTACGTTTTT"))
+	if start != 4 || end != 8 || nerr != 0 {
+		t.Errorf("got start=%d end=%d nerr=%d, want start=4 end=8 nerr=0", start, end, nerr)
+	}
+}
+
+func TestLocatePatternOneMismatch(t *testing.T) {
+	start, end, nerr := LocatePattern("id", []byte("ACGT"), []byte("TTTTACTTTTTT"))
+	if nerr != 1 {
+		t.Errorf("got nerr=%d, want 1 (start=%d end=%d)", nerr, start, end)
+	}
+}
+
+// The real-world case that used to panic: pattern longer than the sequence
+// fragment extracted for indel relocation.
+func TestLocatePatternPatternLongerThanSequence(t *testing.T) {
+	start, end, nerr := LocatePattern("id",
+		[]byte("GGGCAATCCTGAGCCAAATC"),
+		[]byte("tcctgagccaaatcacgtt"))
+
+	if start != -1 || end != -1 || nerr != -1 {
+		t.Errorf("got start=%d end=%d nerr=%d, want the (-1,-1,-1) sentinel", start, end, nerr)
+	}
+}
+
+func TestLocatePatternSequenceLengthOne(t *testing.T) {
+	start, end, nerr := LocatePattern("id", []byte("AB"), []byte("A"))
+
+	if start < 0 || end < 0 || nerr < 0 {
+		t.Fatalf("got start=%d end=%d nerr=%d, expected a valid (non-sentinel) result", start, end, nerr)
+	}
+	if start != 0 || end != 1 || nerr != 1 {
+		t.Errorf("got start=%d end=%d nerr=%d, want start=0 end=1 nerr=1", start, end, nerr)
+	}
+}
+
+// A pattern much longer than the sequence can still yield a mathematically
+// valid (in-bounds) alignment: the extra pattern length is absorbed as gaps,
+// driving the error count high enough that the caller's maxerr threshold
+// rejects it. The function itself must still return consistent bounds.
+func TestLocatePatternPatternMuchLongerThanSequence(t *testing.T) {
+	start, end, nerr := LocatePattern("id", []byte("ACGTACGTACGTACGTACGT"), []byte("ACG"))
+
+	isSentinel := start == -1 && end == -1 && nerr == -1
+	isValid := start >= 0 && end > start && end <= 3 && nerr >= 0
+
+	if !isSentinel && !isValid {
+		t.Errorf("got start=%d end=%d nerr=%d, want either the sentinel or consistent in-bounds values", start, end, nerr)
+	}
+}
+
+func TestLocatePatternNeverReturnsOutOfBounds(t *testing.T) {
+	patterns := []string{"A", "AC", "ACG", "ACGT", "ACGTA", "ACGTAC", "ACGTACG", "ACGTACGT"}
+	sequences := []string{"A", "AC", "ACG", "ACGT", "ACGTA", "ACGTAC", "ACGTACG", "ACGTACGT"}
+
+	for _, p := range patterns {
+		for _, s := range sequences {
+			start, end, nerr := LocatePattern("id", []byte(p), []byte(s))
+
+			if start == -1 && end == -1 && nerr == -1 {
+				// Explicit "no reliable match" sentinel: always acceptable.
+				continue
+			}
+
+			if start < 0 || end < 0 || start >= end || end > len(s) || nerr < 0 {
+				t.Errorf("pattern=%q sequence=%q -> start=%d end=%d nerr=%d is out of bounds / inconsistent",
+					p, s, start, end, nerr)
+			}
+		}
+	}
+}
+
+// Randomized property test over a wide range of pattern/sequence length
+// combinations, including pattern >= sequence, to make sure the function
+// never panics and never returns anything but the sentinel or fully
+// consistent, in-bounds coordinates.
+func TestLocatePatternRandomizedNeverInvalid(t *testing.T) {
+	const bases = "ACGT"
+	rng := rand.New(rand.NewSource(42))
+
+	randSeq := func(n int) []byte {
+		b := make([]byte, n)
+		for i := range b {
+			b[i] = bases[rng.Intn(len(bases))]
+		}
+		return b
+	}
+
+	for trial := 0; trial < 5000; trial++ {
+		patLen := 1 + rng.Intn(15)
+		seqLen := 1 + rng.Intn(15)
+
+		pattern := randSeq(patLen)
+		sequence := randSeq(seqLen)
+
+		func() {
+			defer func() {
+				if r := recover(); r != nil {
+					t.Fatalf("panic for pattern=%q sequence=%q: %v", pattern, sequence, r)
+				}
+			}()
+
+			start, end, nerr := LocatePattern("id", pattern, sequence)
+
+			isSentinel := start == -1 && end == -1 && nerr == -1
+			isValid := start >= 0 && end > start && end <= len(sequence) && nerr >= 0
+
+			if !isSentinel && !isValid {
+				t.Errorf("pattern=%q sequence=%q -> start=%d end=%d nerr=%d is neither the sentinel nor consistent",
+					pattern, sequence, start, end, nerr)
+			}
+		}()
+	}
+}

pkg/obiapat/pattern.go

@@ -373,6 +373,7 @@ func (pattern ApatPattern) BestMatch(sequence ApatSequence, begin, length int) (
 
 	cpattern := (*[1 << 30]byte)(unsafe.Pointer(pattern.pointer.pointer.cpat))
 	frg := sequence.pointer.reference.Sequence()[start:end]
+	fragStart := start
 
 	log.Debugln(
 		string(frg),
@@ -384,11 +385,20 @@ func (pattern ApatPattern) BestMatch(sequence ApatSequence, begin, length int) (
 		(*cpattern)[0:int(pattern.pointer.pointer.patlen)],
 		frg)
 
-	// olderr := m[2]
+	if from < 0 {
+		// obialign.LocatePattern could not reconstruct a reliable
+		// alignment (e.g. the fragment is too short relative to the
+		// pattern). Reporting a guessed position would risk placing
+		// the primer boundary incorrectly, so treat it as no match
+		// at all rather than falling back to an unrefined position.
+		matched = false
+		log.Debugln("No reliable indel relocation, discarding match", sequence.pointer.reference.Id())
+		return
+	}
 
 	nerr = score
-	start = start + from
-	end = start + to
+	start = fragStart + from
+	end = fragStart + to
 	log.Debugf("BestMatch on %s : score=%d [%d..%d]", sequence.pointer.reference.Id(), score, start, nerr)
 	return
 }
@@ -467,6 +477,7 @@ func (pattern ApatPattern) AllMatches(sequence ApatSequence, begin, length int)
 	for _, m := range res {
 		// Recompute the start and end position of the match
 		// when the pattern allows for indels
+		valid := true
 		if m[2] > 0 && pattern.pointer.pointer.hasIndel {
 			// obilog.Warnf("Locating indel on sequence %s[%s]", sequence.pointer.reference.Id(), pattern.String())
 			start := m[0] - m[2]*2
@@ -485,16 +496,26 @@ func (pattern ApatPattern) AllMatches(sequence ApatSequence, begin, length int)
 				(*cpattern)[0:int(pattern.pointer.pointer.patlen)],
 				frg)
 
-			// olderr := m[2]
-			m[2] = score
-			m[0] = start + pb
-			m[1] = start + pe
+			if pb < 0 {
+				// obialign.LocatePattern could not reconstruct a
+				// reliable alignment (e.g. the match sits too close
+				// to a sequence end for the fragment to be usable).
+				// Reporting a guessed position risks placing the
+				// primer boundary incorrectly, so drop the match
+				// entirely instead of keeping an unrefined guess.
+				valid = false
+			} else {
+				// olderr := m[2]
+				m[2] = score
+				m[0] = start + pb
+				m[1] = start + pe
 
-			// obilog.Warnf("seq[%d@%d:%d] %d: %s %d - %s:%s:%s", i, m[0], m[1], olderr, sequence.pointer.reference.Id(), score,
-			// 	frg, (*cpattern)[0:int(pattern.pointer.pointer.patlen)], sequence.pointer.reference.Sequence()[m[0]:m[1]])
+				// obilog.Warnf("seq[%d@%d:%d] %d: %s %d - %s:%s:%s", i, m[0], m[1], olderr, sequence.pointer.reference.Id(), score,
+				// 	frg, (*cpattern)[0:int(pattern.pointer.pointer.patlen)], sequence.pointer.reference.Sequence()[m[0]:m[1]])
+			}
 		}
 
-		if int(pattern.pointer.pointer.maxerr) >= m[2] {
+		if valid && int(pattern.pointer.pointer.maxerr) >= m[2] {
 			res[j] = m
 			j++
 		}

pkg/obiformats/fastqseq_read.go

@@ -131,7 +131,7 @@ func _storeSequenceQuality(bytes *bytes.Buffer, out *obiseq.BioSequence, quality
 	out.SetQualities(q)
 }
 
-func FastqChunkParser(quality_shift byte, with_quality bool, UtoT bool) func(string, io.Reader) (obiseq.BioSequenceSlice, error) {
+func FastqChunkParser(quality_shift byte, with_quality bool, UtoT bool, fileName string) func(string, io.Reader) (obiseq.BioSequenceSlice, error) {
 	parser := func(source string, input io.Reader) (obiseq.BioSequenceSlice, error) {
 
 		var identifier string
@@ -160,12 +160,12 @@ func FastqChunkParser(quality_shift byte, with_quality bool, UtoT bool) func(str
 					// Beginning of sequence
 					state = 1
 				} else {
-					log.Fatalf("%s : sequence entry is not starting with @", source)
+					log.Fatalf("file %s: sequence entry is not starting with @", fileName)
 				}
 			case 1: // Beginning of identifier (Mandatory)
 				if is_sep {
 					// No identifier -> ERROR
-					log.Fatalf("%s : sequence identifier is empty", source)
+					log.Fatalf("file %s: sequence identifier is empty", fileName)
 				} else {
 					// Beginning of identifier
 					state = 2
@@ -221,7 +221,7 @@ func FastqChunkParser(quality_shift byte, with_quality bool, UtoT bool) func(str
 					// End of sequence
 					rawseq := seqBytes.Bytes()
 					if len(rawseq) == 0 {
-						log.Fatalf("@%s[%s] : sequence is empty", identifier, source)
+						log.Fatalf("file %s: record @%s has an empty sequence line", fileName, identifier)
 					}
 					s := obiseq.NewBioSequence(identifier, rawseq, definition)
 					s.SetSource(source)
@@ -241,8 +241,8 @@ func FastqChunkParser(quality_shift byte, with_quality bool, UtoT bool) func(str
 						context = append(
 							append([]byte{previous}, C),
 							context...)
-						log.Fatalf("%s [%s]: sequence contains invalid character %c (%s)",
-							source, identifier, C, string(context))
+						log.Fatalf("file %s: record @%s contains invalid character %c (%s)",
+							fileName, identifier, C, string(context))
 					}
 				}
 			case 7:
@@ -251,7 +251,7 @@ func FastqChunkParser(quality_shift byte, with_quality bool, UtoT bool) func(str
 				} else if C == '+' {
 					state = 8
 				} else {
-					log.Fatalf("@%s[%s] : sequence data not followed by a line starting with + but a %c", identifier, source, C)
+					log.Fatalf("file %s: record @%s: sequence data not followed by a line starting with + but a %c", fileName, identifier, C)
 				}
 			case 8:
 				// State consuming the + internal header line
@@ -282,7 +282,7 @@ func FastqChunkParser(quality_shift byte, with_quality bool, UtoT bool) func(str
 				} else if C == '@' {
 					state = 1
 				} else {
-					log.Fatalf("%s[%s] : sequence record not followed by a line starting with @", identifier, source)
+					log.Fatalf("file %s: record @%s not followed by a line starting with @", fileName, identifier)
 				}
 
 			}
@@ -304,7 +304,7 @@ func FastqChunkParser(quality_shift byte, with_quality bool, UtoT bool) func(str
 }
 
 // FastqChunkParserRope parses a FASTQ chunk directly from a rope without Pack().
-func FastqChunkParserRope(source string, rope *PieceOfChunk, quality_shift byte, with_quality, UtoT bool) (obiseq.BioSequenceSlice, error) {
+func FastqChunkParserRope(source string, rope *PieceOfChunk, quality_shift byte, with_quality, UtoT bool, fileName string) (obiseq.BioSequenceSlice, error) {
 	scanner := newRopeScanner(rope)
 	sequences := obiseq.MakeBioSequenceSlice(100)[:0]
 
@@ -334,7 +334,7 @@ func FastqChunkParserRope(source string, rope *PieceOfChunk, quality_shift byte,
 		// Line 2: sequence
 		sline := scanner.ReadLine()
 		if sline == nil {
-			log.Fatalf("@%s[%s]: unexpected EOF after header", id, source)
+			log.Fatalf("file %s: record @%s is truncated (header line with no sequence line following) — the FASTQ file appears incomplete", fileName, id)
 		}
 		seqDest := make([]byte, len(sline))
 		w := 0
@@ -350,7 +350,7 @@ func FastqChunkParserRope(source string, rope *PieceOfChunk, quality_shift byte,
 		}
 		seqDest = seqDest[:w]
 		if len(seqDest) == 0 {
-			log.Fatalf("@%s[%s]: sequence is empty", id, source)
+			log.Fatalf("file %s: record @%s has an empty sequence line", fileName, id)
 		}
 
 		// Line 3: + (skip)
@@ -382,16 +382,17 @@ func _ParseFastqFile(
 	out obiiter.IBioSequence,
 	quality_shift byte,
 	with_quality, UtoT bool,
+	fileName string,
 ) {
 
-	parser := FastqChunkParser(quality_shift, with_quality, UtoT)
+	parser := FastqChunkParser(quality_shift, with_quality, UtoT, fileName)
 
 	for chunks := range input {
 		var sequences obiseq.BioSequenceSlice
 		var err error
 
 		if chunks.Rope != nil {
-			sequences, err = FastqChunkParserRope(chunks.Source, chunks.Rope, quality_shift, with_quality, UtoT)
+			sequences, err = FastqChunkParserRope(chunks.Source, chunks.Rope, quality_shift, with_quality, UtoT, fileName)
 		} else {
 			sequences, err = parser(chunks.Source, chunks.Raw)
 		}
@@ -423,6 +424,8 @@ func ReadFastq(reader io.Reader, options ...WithOption) (obiiter.IBioSequence, e
 		false,
 	)
 
+	fileName := opt.FileName()
+
 	for i := 0; i < nworker; i++ {
 		out.Add(1)
 		go _ParseFastqFile(
@@ -431,6 +434,7 @@ func ReadFastq(reader io.Reader, options ...WithOption) (obiiter.IBioSequence, e
 			obidefault.ReadQualitiesShift(),
 			opt.ReadQualities(),
 			opt.UtoT(),
+			fileName,
 		)
 	}
 
@@ -456,7 +460,9 @@ func ReadFastq(reader io.Reader, options ...WithOption) (obiiter.IBioSequence, e
 }
 
 func ReadFastqFromFile(filename string, options ...WithOption) (obiiter.IBioSequence, error) {
-	options = append(options, OptionsSource(obiutils.RemoveAllExt((path.Base(filename)))))
+	options = append(options,
+		OptionsSource(obiutils.RemoveAllExt((path.Base(filename)))),
+		OptionsFileName(filename))
 
 	file, err := obiutils.Ropen(filename)
 

pkg/obiformats/fastseq_json_header.go

@@ -199,8 +199,111 @@ func _parse_json_array_interface(str []byte) ([]interface{}, error) {
 	return values, nil
 }
 
-func _parse_json_header_(header string, sequence *obiseq.BioSequence) string {
+// _parse_json_annotation_field parses a single key/value pair coming from a
+// JSON object (either a FASTA/FASTQ inline JSON header, or the "annotations"
+// field of a JSON sequence record) and applies it to the sequence, special
+// casing the well-known OBITools attributes (id, definition, count, taxid,
+// obiclean_*, merged_*).
+func _parse_json_annotation_field(key []byte, value []byte, dataType jsonparser.ValueType, sequence *obiseq.BioSequence) error {
 	annotations := sequence.Annotations()
+	var err error
+
+	skey := obiutils.UnsafeString(key)
+
+	switch {
+	case skey == "id":
+		sequence.SetId(string(value))
+	case skey == "definition":
+		sequence.SetDefinition(string(value))
+
+	case skey == "count":
+		if dataType != jsonparser.Number {
+			log.Fatalf("%s: Count attribut must be numeric: %s", sequence.Id(), string(value))
+		}
+		count, err := jsonparser.ParseInt(value)
+		if err != nil {
+			log.Fatalf("%s: Cannot parse count %s", sequence.Id(), string(value))
+		}
+		sequence.SetCount(int(count))
+
+	case skey == "obiclean_weight":
+		weight, err := _parse_json_map_int(value)
+		if err != nil {
+			log.Fatalf("%s: Cannot parse obiclean weight %s", sequence.Id(), string(value))
+		}
+		annotations[skey] = weight
+
+	case skey == "obiclean_status":
+		status, err := _parse_json_map_string(value)
+		if err != nil {
+			log.Fatalf("%s: Cannot parse obiclean status %s", sequence.Id(), string(value))
+		}
+		annotations[skey] = status
+
+	case strings.HasPrefix(skey, "merged_"):
+		if dataType == jsonparser.Object {
+			data, err := _parse_json_map_int(value)
+			if err != nil {
+				log.Fatalf("%s: Cannot parse merged slot %s: %v", sequence.Id(), skey, err)
+			} else {
+				annotations[skey] = obiseq.MapAsStatsOnValues(data)
+			}
+		} else {
+			log.Fatalf("%s: Cannot parse merged slot %s", sequence.Id(), skey)
+		}
+
+	case skey == "taxid":
+		if dataType == jsonparser.Number || dataType == jsonparser.String {
+			taxid := string(value)
+			sequence.SetTaxid(taxid)
+		} else {
+			log.Fatalf("%s: Cannot parse taxid %s", sequence.Id(), string(value))
+		}
+
+	case strings.HasSuffix(skey, "_taxid"):
+		if dataType == jsonparser.Number || dataType == jsonparser.String {
+			rank := skey[:len(skey)-len("_taxid")]
+
+			taxid := string(value)
+			sequence.SetTaxid(taxid, rank)
+		} else {
+			log.Fatalf("%s: Cannot parse taxid %s", sequence.Id(), string(value))
+		}
+
+	default:
+		skey = strings.Clone(skey)
+		switch dataType {
+		case jsonparser.String:
+			annotations[skey] = string(value)
+		case jsonparser.Number:
+			// Try to parse the number as an int at first then as float if that fails.
+			annotations[skey], err = jsonparser.ParseInt(value)
+			if err != nil {
+				annotations[skey], err = strconv.ParseFloat(obiutils.UnsafeString(value), 64)
+			}
+		case jsonparser.Array:
+			annotations[skey], err = _parse_json_array_interface(value)
+		case jsonparser.Object:
+			annotations[skey], err = _parse_json_map_interface(value)
+		case jsonparser.Boolean:
+			annotations[skey], err = jsonparser.ParseBoolean(value)
+		case jsonparser.Null:
+			annotations[skey] = nil
+		default:
+			log.Fatalf("Unknown data type %v", dataType)
+		}
+	}
+
+	if err != nil {
+		annotations[skey] = "NaN"
+		log.Fatalf("%s: Cannot parse value %s assicated to key %s into a %s value",
+			sequence.Id(), string(value), skey, dataType.String())
+	}
+
+	return err
+}
+
+func _parse_json_header_(header string, sequence *obiseq.BioSequence) string {
 	start := -1
 	stop := -1
 	level := 0
@@ -240,101 +343,7 @@ func _parse_json_header_(header string, sequence *obiseq.BioSequence) string {
 
 	jsonparser.ObjectEach(obiutils.UnsafeBytes(header[start:stop]),
 		func(key []byte, value []byte, dataType jsonparser.ValueType, offset int) error {
-			var err error
-
-			skey := obiutils.UnsafeString(key)
-
-			switch {
-			case skey == "id":
-				sequence.SetId(string(value))
-			case skey == "definition":
-				sequence.SetDefinition(string(value))
-
-			case skey == "count":
-				if dataType != jsonparser.Number {
-					log.Fatalf("%s: Count attribut must be numeric: %s", sequence.Id(), string(value))
-				}
-				count, err := jsonparser.ParseInt(value)
-				if err != nil {
-					log.Fatalf("%s: Cannot parse count %s", sequence.Id(), string(value))
-				}
-				sequence.SetCount(int(count))
-
-			case skey == "obiclean_weight":
-				weight, err := _parse_json_map_int(value)
-				if err != nil {
-					log.Fatalf("%s: Cannot parse obiclean weight %s", sequence.Id(), string(value))
-				}
-				annotations[skey] = weight
-
-			case skey == "obiclean_status":
-				status, err := _parse_json_map_string(value)
-				if err != nil {
-					log.Fatalf("%s: Cannot parse obiclean status %s", sequence.Id(), string(value))
-				}
-				annotations[skey] = status
-
-			case strings.HasPrefix(skey, "merged_"):
-				if dataType == jsonparser.Object {
-					data, err := _parse_json_map_int(value)
-					if err != nil {
-						log.Fatalf("%s: Cannot parse merged slot %s: %v", sequence.Id(), skey, err)
-					} else {
-						annotations[skey] = obiseq.MapAsStatsOnValues(data)
-					}
-				} else {
-					log.Fatalf("%s: Cannot parse merged slot %s", sequence.Id(), skey)
-				}
-
-			case skey == "taxid":
-				if dataType == jsonparser.Number || dataType == jsonparser.String {
-					taxid := string(value)
-					sequence.SetTaxid(taxid)
-				} else {
-					log.Fatalf("%s: Cannot parse taxid %s", sequence.Id(), string(value))
-				}
-
-			case strings.HasSuffix(skey, "_taxid"):
-				if dataType == jsonparser.Number || dataType == jsonparser.String {
-					rank := skey[:len(skey)-len("_taxid")]
-
-					taxid := string(value)
-					sequence.SetTaxid(taxid, rank)
-				} else {
-					log.Fatalf("%s: Cannot parse taxid %s", sequence.Id(), string(value))
-				}
-
-			default:
-				skey = strings.Clone(skey)
-				switch dataType {
-				case jsonparser.String:
-					annotations[skey] = string(value)
-				case jsonparser.Number:
-					// Try to parse the number as an int at first then as float if that fails.
-					annotations[skey], err = jsonparser.ParseInt(value)
-					if err != nil {
-						annotations[skey], err = strconv.ParseFloat(obiutils.UnsafeString(value), 64)
-					}
-				case jsonparser.Array:
-					annotations[skey], err = _parse_json_array_interface(value)
-				case jsonparser.Object:
-					annotations[skey], err = _parse_json_map_interface(value)
-				case jsonparser.Boolean:
-					annotations[skey], err = jsonparser.ParseBoolean(value)
-				case jsonparser.Null:
-					annotations[skey] = nil
-				default:
-					log.Fatalf("Unknown data type %v", dataType)
-				}
-			}
-
-			if err != nil {
-				annotations[skey] = "NaN"
-				log.Fatalf("%s: Cannot parse value %s assicated to key %s into a %s value",
-					sequence.Id(), string(value), skey, dataType.String())
-			}
-
-			return err
+			return _parse_json_annotation_field(key, value, dataType, sequence)
 		},
 	)
 

pkg/obiformats/json_read.go

@@ -0,0 +1,147 @@
+package obiformats
+
+import (
+	"io"
+	"os"
+	"path"
+
+	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obidefault"
+	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiiter"
+	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiseq"
+	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiutils"
+	"github.com/buger/jsonparser"
+	"github.com/goccy/go-json"
+	log "github.com/sirupsen/logrus"
+)
+
+// _parse_json_record parses a single JSON object describing a sequence
+// (as produced by JSONRecord in json_writer.go) into a *obiseq.BioSequence.
+func _parse_json_record(raw []byte, shift byte) *obiseq.BioSequence {
+	sequence := obiseq.NewEmptyBioSequence(0)
+
+	if id, err := jsonparser.GetString(raw, "id"); err == nil {
+		sequence.SetId(id)
+	}
+
+	if seq, err := jsonparser.GetString(raw, "sequence"); err == nil {
+		sequence.SetSequence([]byte(seq))
+	}
+
+	if qual, err := jsonparser.GetString(raw, "qualities"); err == nil {
+		q := []byte(qual)
+		for i := 0; i < len(q); i++ {
+			q[i] -= shift
+		}
+		sequence.SetQualities(q)
+	}
+
+	if annot, dataType, _, err := jsonparser.Get(raw, "annotations"); err == nil && dataType == jsonparser.Object {
+		jsonparser.ObjectEach(annot,
+			func(key []byte, value []byte, valType jsonparser.ValueType, offset int) error {
+				return _parse_json_annotation_field(key, value, valType, sequence)
+			},
+		)
+	}
+
+	return sequence
+}
+
+// _ParseJsonFile streams the top-level JSON array, decoding and pushing one
+// batch of sequences at a time, without ever loading the whole document in
+// memory. Only one raw record at a time is buffered by the decoder.
+func _ParseJsonFile(source string,
+	reader io.Reader,
+	out obiiter.IBioSequence,
+	shift byte,
+	batchSize int) {
+
+	dec := json.NewDecoder(reader)
+
+	if _, err := dec.Token(); err != nil {
+		if err == io.EOF {
+			out.Done()
+			return
+		}
+		log.Fatalf("cannot parse JSON data: %v", err)
+	}
+
+	slice := obiseq.MakeBioSequenceSlice()
+	o := 0
+
+	for dec.More() {
+		var raw json.RawMessage
+
+		if err := dec.Decode(&raw); err != nil {
+			log.Fatalf("cannot parse JSON data: %v", err)
+		}
+
+		sequence := _parse_json_record(raw, shift)
+
+		slice = append(slice, sequence)
+		if len(slice) >= batchSize {
+			out.Push(obiiter.MakeBioSequenceBatch(source, o, slice))
+			o++
+			slice = obiseq.MakeBioSequenceSlice()
+		}
+	}
+
+	if len(slice) > 0 {
+		out.Push(obiiter.MakeBioSequenceBatch(source, o, slice))
+	}
+
+	out.Done()
+}
+
+func ReadJSON(reader io.Reader, options ...WithOption) (obiiter.IBioSequence, error) {
+
+	opt := MakeOptions(options)
+	out := obiiter.MakeIBioSequence()
+
+	out.Add(1)
+	go _ParseJsonFile(opt.Source(),
+		reader,
+		out,
+		obidefault.ReadQualitiesShift(),
+		opt.BatchSize())
+
+	go func() {
+		out.WaitAndClose()
+	}()
+
+	return out, nil
+
+}
+
+func ReadJSONFromFile(filename string, options ...WithOption) (obiiter.IBioSequence, error) {
+
+	options = append(options, OptionsSource(obiutils.RemoveAllExt((path.Base(filename)))))
+	file, err := obiutils.Ropen(filename)
+
+	if err == obiutils.ErrNoContent {
+		log.Infof("file %s is empty", filename)
+		return ReadEmptyFile(options...)
+	}
+
+	if err != nil {
+		return obiiter.NilIBioSequence, err
+	}
+
+	return ReadJSON(file, options...)
+}
+
+func ReadJSONFromStdin(reader io.Reader, options ...WithOption) (obiiter.IBioSequence, error) {
+	options = append(options, OptionsSource(obiutils.RemoveAllExt("stdin")))
+	input, err := obiutils.Buf(os.Stdin)
+
+	if err == obiutils.ErrNoContent {
+		log.Infof("stdin is empty")
+		return ReadEmptyFile(options...)
+	}
+
+	if err != nil {
+		log.Fatalf("open file error: %v", err)
+		return obiiter.NilIBioSequence, err
+	}
+
+	return ReadJSON(input, options...)
+}

pkg/obiformats/options.go

@@ -35,6 +35,7 @@ type __options__ struct {
 	csv_auto              bool
 	paired_filename       string
 	source                string
+	filename              string
 	with_feature_table    bool
 	with_pattern          bool
 	with_parent           bool
@@ -216,6 +217,16 @@ func (opt Options) Source() string {
 	return opt.pointer.source
 }
 
+// FileName returns the full path of the file being read, for use in
+// diagnostic messages. It falls back to Source() when no explicit
+// file name has been set (e.g. reading from stdin or a raw reader).
+func (opt Options) FileName() string {
+	if opt.pointer.filename == "" {
+		return opt.pointer.source
+	}
+	return opt.pointer.filename
+}
+
 func (opt Options) WithFeatureTable() bool {
 	return opt.pointer.with_feature_table
 }
@@ -421,6 +432,14 @@ func OptionsSource(source string) WithOption {
 	return f
 }
 
+func OptionsFileName(filename string) WithOption {
+	f := WithOption(func(opt Options) {
+		opt.pointer.filename = filename
+	})
+
+	return f
+}
+
 func OptionsWithProgressBar() WithOption {
 	f := WithOption(func(opt Options) {
 		opt.pointer.with_progress_bar = true

pkg/obiformats/universal_read.go

@@ -145,6 +145,8 @@ func ReadSequencesFromFile(filename string,
 		return ReadGenbank(reader, options...)
 	case "text/csv":
 		return ReadCSV(reader, options...)
+	case "application/json":
+		return ReadJSON(reader, options...)
 	default:
 		log.Fatalf("File %s has guessed format %s which is not yet implemented",
 			filename, mime.String())

pkg/obifp/uint128_test.go

@@ -134,7 +134,7 @@ func TestUint128_QuoRem(t *testing.T) {
 	u := Uint128{w1: 3, w0: 8}
 	v := Uint128{w1: 0, w0: 4}
 	q, r := u.QuoRem(v)
-	assert.Equal(t, Uint128{w1: 0, w0: 2}, q)
+	assert.Equal(t, Uint128{w1: 0, w0: 13835058055282163714}, q)
 	assert.Equal(t, Uint128{w1: 0, w0: 0}, r)
 }
 
@@ -150,7 +150,7 @@ func TestUint128_Div(t *testing.T) {
 	u := Uint128{w1: 3, w0: 8}
 	v := Uint128{w1: 0, w0: 4}
 	q := u.Div(v)
-	assert.Equal(t, Uint128{w1: 0, w0: 2}, q)
+	assert.Equal(t, Uint128{w1: 0, w0: 13835058055282163714}, q)
 }
 
 func TestUint128_Div64(t *testing.T) {
@@ -183,7 +183,7 @@ func TestUint128_Cmp(t *testing.T) {
 func TestUint128_Cmp64(t *testing.T) {
 	u := Uint128{w1: 1, w0: 2}
 	v := uint64(3)
-	assert.Equal(t, -1, u.Cmp64(v))
+	assert.Equal(t, 1, u.Cmp64(v))
 }
 
 func TestUint128_Equals(t *testing.T) {

pkg/obingslibrary/multimatch.go

@@ -777,7 +777,7 @@ func (library *NGSLibrary) ExtractMultiBarcodeSliceWorker(options ...WithOption)
 		library.SetAllowsIndels(true)
 	}
 
-	if opt.AllowedMismatches() > 0 {
+	if opt.AllowedMismatchesIsSet() {
 		library.SetAllowedMismatches(opt.AllowedMismatches())
 	}
 

pkg/obingslibrary/worker.go

@@ -6,13 +6,14 @@ import (
 )
 
 type _Options struct {
-	discardErrors   bool
-	unidentified    string
-	allowedMismatch int
-	allowsIndel     bool
-	withProgressBar bool
-	parallelWorkers int
-	batchSize       int
+	discardErrors      bool
+	unidentified       string
+	allowedMismatch    int
+	allowedMismatchSet bool
+	allowsIndel        bool
+	withProgressBar    bool
+	parallelWorkers    int
+	batchSize          int
 }
 
 // Options stores a set of option usable by the
@@ -52,6 +53,7 @@ func OptionWithProgressBar(yes bool) WithOption {
 func OptionAllowedMismatches(count int) WithOption {
 	f := WithOption(func(opt Options) {
 		opt.pointer.allowedMismatch = count
+		opt.pointer.allowedMismatchSet = true
 	})
 
 	return f
@@ -97,6 +99,12 @@ func (options Options) AllowedMismatches() int {
 	return options.pointer.allowedMismatch
 }
 
+// AllowedMismatchesIsSet returns true if OptionAllowedMismatches
+// was explicitly applied to these options.
+func (options Options) AllowedMismatchesIsSet() bool {
+	return options.pointer.allowedMismatchSet
+}
+
 func (options Options) AllowsIndels() bool {
 	return options.pointer.allowsIndel
 }

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 4.4.46"
+var _Version = "Release 4.5.0"
 
 // Version returns the version of the obitools package.
 //

pkg/obitools/obiconvert/options.go

@@ -24,6 +24,7 @@ var __input_genbank_format__ = false
 var __input_fastq_format__ = false
 var __input_fasta_format__ = false
 var __input_csv_format__ = false
+var __input_json_format__ = false
 
 var __output_in_fasta__ = false
 var __output_in_fastq__ = false
@@ -71,6 +72,9 @@ func InputOptionSet(options *getoptions.GetOpt) {
 	options.BoolVar(&__input_csv_format__, "csv", __input_csv_format__,
 		options.Description("Read data following the CSV format."))
 
+	options.BoolVar(&__input_json_format__, "json", __input_json_format__,
+		options.Description("Read data following the JSON format."))
+
 	options.BoolVar(&__no_ordered_input__, "no-order", __no_ordered_input__,
 		options.Description("When several input files are provided, "+
 			"indicates that there is no order among them."))
@@ -158,6 +162,8 @@ func CLIInputFormat() string {
 		return "genbank"
 	case __input_csv_format__:
 		return "csv"
+	case __input_json_format__:
+		return "json"
 	default:
 		return "guessed"
 	}

pkg/obitools/obiconvert/sequence_reader.go

@@ -73,7 +73,9 @@ func ExpandListOfFiles(check_ext bool, filenames ...string) ([]string, error) {
 						strings.HasSuffix(path, "dat") ||
 						strings.HasSuffix(path, "dat.gz") ||
 						strings.HasSuffix(path, "ecopcr") ||
-						strings.HasSuffix(path, "ecopcr.gz") {
+						strings.HasSuffix(path, "ecopcr.gz") ||
+						strings.HasSuffix(path, "json") ||
+						strings.HasSuffix(path, "json.gz") {
 						log.Debugf("Appending %s file\n", path)
 						list_of_files.Add(path)
 					}
@@ -142,6 +144,8 @@ func CLIReadBioSequences(filenames ...string) (obiiter.IBioSequence, error) {
 			iterator, err = obiformats.ReadFastq(os.Stdin, opts...)
 		case "csv":
 			iterator, err = obiformats.ReadCSV(os.Stdin, opts...)
+		case "json":
+			iterator, err = obiformats.ReadJSON(os.Stdin, opts...)
 		default:
 			iterator, err = obiformats.ReadSequencesFromStdin(opts...)
 		}
@@ -163,6 +167,8 @@ func CLIReadBioSequences(filenames ...string) (obiiter.IBioSequence, error) {
 			reader = obiformats.ReadFastaFromFile
 		case "csv":
 			reader = obiformats.ReadCSVFromFile
+		case "json":
+			reader = obiformats.ReadJSONFromFile
 		case "ecopcr":
 			reader = obiformats.ReadEcoPCRFromFile
 		case "embl":

pkg/obitools/obilandmark/obilandmark.go

@@ -170,7 +170,7 @@ func CLISelectLandmarkSequences(iterator obiiter.IBioSequence) obiiter.IBioSeque
 		for i, seq := range library {
 			taxon := seq.Taxon(taxo)
 			if taxon == nil {
-				log.Fatal("%s: Cannot identify taxid %s in %s", seq.Id(), seq.Taxid(), taxo.Name())
+				log.Fatalf("%s: Cannot identify taxid %s in %s", seq.Id(), seq.Taxid(), taxo.Name())
 			}
 			taxa.Set(i, taxon)
 		}

pkg/obitools/obimultiplex/demultiplex.go

@@ -15,7 +15,6 @@ func IExtractBarcode(iterator obiiter.IBioSequence) (obiiter.IBioSequence, error
 	opts := make([]obingslibrary.WithOption, 0, 10)
 
 	opts = append(opts,
-		obingslibrary.OptionAllowedMismatches(CLIAllowedMismatch()),
 		obingslibrary.OptionAllowedIndel(CLIAllowsIndel()),
 		obingslibrary.OptionUnidentified(CLIUnidentifiedFileName()),
 		obingslibrary.OptionDiscardErrors(!CLIConservedErrors()),
@@ -23,6 +22,14 @@ func IExtractBarcode(iterator obiiter.IBioSequence) (obiiter.IBioSequence, error
 		obingslibrary.OptionBatchSize(obidefault.BatchSize()),
 	)
 
+	// Only propagate the CLI --allowed-mismatches value if the user
+	// explicitly set it: otherwise the per-primer values defined in
+	// the NGSFilter config file (@primer_mismatches, @forward_mismatches,
+	// @reverse_mismatches) must be preserved.
+	if CLIAllowedMismatchIsSet() {
+		opts = append(opts, obingslibrary.OptionAllowedMismatches(CLIAllowedMismatch()))
+	}
+
 	ngsfilter, err := CLINGSFIlter()
 	if err != nil {
 		log.Fatalf("%v", err)

pkg/obitools/obimultiplex/options.go

@@ -18,6 +18,7 @@ var _UnidentifiedFile = ""
 var _AllowedMismatch = 2
 var _AllowsIndel = false
 var _ConservedError = false
+var _optionsParser *getoptions.GetOpt
 
 // PCROptionSet defines every options related to a simulated PCR.
 //
@@ -29,6 +30,8 @@ var _ConservedError = false
 // - option : is a pointer to a getoptions.GetOpt instance normaly
 // produced by the
 func MultiplexOptionSet(options *getoptions.GetOpt) {
+	_optionsParser = options
+
 	options.StringVar(&_NGSFilterFile, "tag-list", _NGSFilterFile,
 		options.Alias("s"),
 		options.Description("File name of the NGSFilter file describing PCRs."))
@@ -62,6 +65,15 @@ func CLIAllowedMismatch() int {
 	return _AllowedMismatch
 }
 
+// CLIAllowedMismatchIsSet returns true if the user explicitly
+// specified --allowed-mismatches on the command line, as opposed
+// to relying on its default value. This allows per-primer mismatch
+// settings from the NGSFilter config file to take precedence unless
+// the user explicitly overrides them from the CLI.
+func CLIAllowedMismatchIsSet() bool {
+	return _optionsParser != nil && _optionsParser.Called("allowed-mismatches")
+}
+
 func CLIAllowsIndel() bool {
 	return _AllowsIndel
 }

pkg/obitools/obitagpcr/pcrtag.go

@@ -55,7 +55,7 @@ func IPCRTagPESequencesBatch(iterator obiiter.IBioSequence,
 		ngsfilter.SetAllowsIndels(true)
 	}
 
-	if obimultiplex.CLIAllowedMismatch() > 0 {
+	if obimultiplex.CLIAllowedMismatchIsSet() {
 		ngsfilter.SetAllowedMismatches(obimultiplex.CLIAllowedMismatch())
 	}
 

pkg/obiutils/mimetypes.go

@@ -102,6 +102,11 @@ func RegisterOBIMimeType() {
 			return ok
 		}
 
+		jsonDetector := func(raw []byte, limit uint32) bool {
+			raw = bytes.TrimLeft(raw, " \t\r\n")
+			return len(raw) > 0 && (raw[0] == '[' || raw[0] == '{')
+		}
+
 		mimetype.Lookup("text/plain").Extend(fastaDetector, "text/fasta", ".fasta")
 		mimetype.Lookup("text/plain").Extend(fastqDetector, "text/fastq", ".fastq")
 		mimetype.Lookup("text/plain").Extend(ecoPCR2Detector, "text/ecopcr2", ".ecopcr")
@@ -115,6 +120,7 @@ func RegisterOBIMimeType() {
 		mimetype.Lookup("application/octet-stream").Extend(genbankDetector, "text/genbank", ".seq")
 		mimetype.Lookup("application/octet-stream").Extend(emblDetector, "text/embl", ".dat")
 		mimetype.Lookup("application/octet-stream").Extend(csv, "text/csv", ".csv")
+		mimetype.Lookup("application/octet-stream").Extend(jsonDetector, "application/json", ".json")
 	}
 	__obimimetype_registred__ = true
 }

version.txt

@@ -1 +1 @@
-4.4.46
+4.5.0