Changes to be committed:

modified:   cmd/obitools/obitag/main.go
	modified:   cmd/obitools/obitaxonomy/main.go
	modified:   pkg/obiformats/csvtaxdump_read.go
	modified:   pkg/obiformats/ecopcr_read.go
	modified:   pkg/obiformats/ncbitaxdump_read.go
	modified:   pkg/obiformats/ncbitaxdump_readtar.go
	modified:   pkg/obiformats/newick_write.go
	modified:   pkg/obiformats/options.go
	modified:   pkg/obiformats/taxonomy_read.go
	modified:   pkg/obiformats/universal_read.go
	modified:   pkg/obiiter/extract_taxonomy.go
	modified:   pkg/obioptions/options.go
	modified:   pkg/obioptions/version.go
	new file:   pkg/obiphylo/tree.go
	modified:   pkg/obiseq/biosequenceslice.go
	modified:   pkg/obiseq/taxonomy_methods.go
	modified:   pkg/obitax/taxonomy.go
	modified:   pkg/obitax/taxonset.go
	modified:   pkg/obitools/obiconvert/sequence_reader.go
	modified:   pkg/obitools/obitag/obitag.go
	modified:   pkg/obitools/obitaxonomy/obitaxonomy.go
	modified:   pkg/obitools/obitaxonomy/options.go
	deleted:    sample/.DS_Store

pkg/obiformats/csvtaxdump_read.go

@@ -10,7 +10,7 @@ import (
 	log "github.com/sirupsen/logrus"
 )
 
-func LoadCSVTaxonomy(path string, onlysn bool) (*obitax.Taxonomy, error) {
+func LoadCSVTaxonomy(path string, onlysn, seqAsTaxa bool) (*obitax.Taxonomy, error) {
 
 	log.Infof("Loading taxonomy from csv file: %s", path)
 

pkg/obiformats/ecopcr_read.go

@@ -4,13 +4,10 @@ import (
 	"encoding/csv"
 	"fmt"
 	"io"
-	"os"
 	"path"
 	"strconv"
 	"strings"
 
-	gzip "github.com/klauspost/pgzip"
-
 	log "github.com/sirupsen/logrus"
 
 	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiiter"
@@ -177,8 +174,10 @@ func ReadEcoPCR(reader io.Reader, options ...WithOption) (obiiter.IBioSequence,
 	}()
 
 	go func() {
+		var err error = nil
+		var seq *obiseq.BioSequence
 
-		seq, err := __read_ecopcr_bioseq__(&ecopcr)
+		seq, err = __read_ecopcr_bioseq__(&ecopcr)
 		seq.SetSource(opt.Source())
 		slice := make(obiseq.BioSequenceSlice, 0, opt.BatchSize())
 		i := 0
@@ -194,7 +193,12 @@ func ReadEcoPCR(reader io.Reader, options ...WithOption) (obiiter.IBioSequence,
 			}
 
 			seq, err = __read_ecopcr_bioseq__(&ecopcr)
-			seq.SetSource(opt.Source())
+
+			if err == nil {
+				seq.SetSource(opt.Source())
+			} else if err != io.EOF {
+				log.Panicf("%+v", err)
+			}
 		}
 
 		if len(slice) > 0 {
@@ -218,22 +222,21 @@ func ReadEcoPCR(reader io.Reader, options ...WithOption) (obiiter.IBioSequence,
 
 func ReadEcoPCRFromFile(filename string, options ...WithOption) (obiiter.IBioSequence, error) {
 	var reader io.Reader
-	var greader io.Reader
 	var err error
 
 	options = append(options, OptionsSource(obiutils.RemoveAllExt((path.Base(filename)))))
 
-	reader, err = os.Open(filename)
+	reader, err = obiutils.Ropen(filename)
+
+	if err == obiutils.ErrNoContent {
+		log.Infof("file %s is empty", filename)
+		return ReadEmptyFile(options...)
+	}
+
 	if err != nil {
 		log.Printf("open file error: %+v", err)
 		return obiiter.NilIBioSequence, err
 	}
 
-	// Test if the flux is compressed by gzip
-	greader, err = gzip.NewReader(reader)
-	if err == nil {
-		reader = greader
-	}
-
 	return ReadEcoPCR(reader, options...)
 }

pkg/obiformats/ncbitaxdump_read.go

@@ -149,7 +149,7 @@ func loadMergedTable(reader io.Reader, taxonomy *obitax.Taxonomy) int {
 // Returns:
 //   - A pointer to the obitax.Taxonomy object containing the loaded taxonomy data, or an error
 //     if any of the files cannot be opened or read.
-func LoadNCBITaxDump(directory string, onlysn bool) (*obitax.Taxonomy, error) {
+func LoadNCBITaxDump(directory string, onlysn, seqAsTaxa bool) (*obitax.Taxonomy, error) {
 
 	taxonomy := obitax.NewTaxonomy("NCBI Taxonomy", "taxon", obiutils.AsciiDigitSet)
 

pkg/obiformats/ncbitaxdump_readtar.go

@@ -63,7 +63,7 @@ func IsNCBITarTaxDump(path string) bool {
 	return citations && division && gencode && names && delnodes && gc && merged && nodes
 }
 
-func LoadNCBITarTaxDump(path string, onlysn bool) (*obitax.Taxonomy, error) {
+func LoadNCBITarTaxDump(path string, onlysn, seqAsTaxa bool) (*obitax.Taxonomy, error) {
 
 	taxonomy := obitax.NewTaxonomy("NCBI Taxonomy", "taxon", obiutils.AsciiDigitSet)
 

pkg/obiformats/newick_write.go

@@ -54,7 +54,7 @@ func (tree *Tree) Newick(level int, taxid, scientific_name, rank bool) string {
 		if scientific_name {
 			buffer.WriteByte(' ')
 		}
-		buffer.WriteByte('-')
+		// buffer.WriteByte('-')
 		if taxid {
 			buffer.WriteString(*tree.TaxNode.Id())
 			if rank {
@@ -64,7 +64,7 @@ func (tree *Tree) Newick(level int, taxid, scientific_name, rank bool) string {
 		if rank {
 			buffer.WriteString(tree.TaxNode.Rank())
 		}
-		buffer.WriteByte('-')
+		//buffer.WriteByte('-')
 	}
 	if scientific_name || taxid || rank {
 		buffer.WriteByte('\'')
@@ -85,24 +85,14 @@ func Newick(taxa *obitax.TaxonSet, taxid, scientific_name, rank bool) string {
 		return ""
 	}
 
-	iterator := taxa.Sort().Iterator()
+	root := taxa.Sort().Get(0)
+	tree, err := taxa.AsPhyloTree(root)
 
-	nodes := make(map[*string]*Tree, taxa.Len())
-	trees := make([]*Tree, 0)
-
-	for iterator.Next() {
-		taxon := iterator.Get()
-
-		tree := &Tree{TaxNode: taxon.Node}
-		if parent, ok := nodes[taxon.Parent().Node.Id()]; ok {
-			parent.Children = append(parent.Children, tree)
-		} else {
-			trees = append(trees, tree)
-		}
-		nodes[taxon.Node.Id()] = tree
+	if err != nil {
+		log.Fatalf("Cannot build taxonomy tree: %v", err)
 	}
 
-	return trees[0].Newick(0, taxid, scientific_name, rank)
+	return tree.Newick(0)
 }
 
 func WriteNewick(iterator *obitax.ITaxon,

pkg/obiformats/options.go

@@ -42,6 +42,7 @@ type __options__ struct {
 	with_rank             bool
 	with_taxid            bool
 	with_scientific_name  bool
+	without_root_path     bool
 	raw_taxid             bool
 	with_metadata         []string
 }
@@ -88,6 +89,7 @@ func MakeOptions(setters []WithOption) Options {
 		with_rank:             true,
 		with_taxid:            true,
 		with_scientific_name:  false,
+		without_root_path:     false,
 		raw_taxid:             false,
 	}
 
@@ -250,6 +252,11 @@ func (o *Options) WithScientificName() bool {
 	return o.pointer.with_scientific_name
 }
 
+// WithoutRootPath returns whether the root path option is enabled.
+func (o *Options) WithoutRootPath() bool {
+	return o.pointer.without_root_path
+}
+
 // RawTaxid returns whether the raw taxid option is enabled.
 // It retrieves the setting from the underlying options.
 func (o *Options) RawTaxid() bool {
@@ -576,6 +583,13 @@ func OptionsWithScientificName(value bool) WithOption {
 	return f
 }
 
+func OptionWithoutRootPath(value bool) WithOption {
+	f := WithOption(func(opt Options) {
+		opt.pointer.without_root_path = value
+	})
+	return f
+}
+
 func OptionsRawTaxid(value bool) WithOption {
 	f := WithOption(func(opt Options) {
 		opt.pointer.raw_taxid = value

pkg/obiformats/taxonomy_read.go

@@ -11,7 +11,7 @@ import (
 	log "github.com/sirupsen/logrus"
 )
 
-type TaxonomyLoader func(path string, onlysn bool) (*obitax.Taxonomy, error)
+type TaxonomyLoader func(path string, onlysn, seqAsTaxa bool) (*obitax.Taxonomy, error)
 
 func DetectTaxonomyTarFormat(path string) (TaxonomyLoader, error) {
 
@@ -67,26 +67,28 @@ func DetectTaxonomyFormat(path string) (TaxonomyLoader, error) {
 		case "application/x-tar":
 			return DetectTaxonomyTarFormat(path)
 		case "text/fasta":
-			return func(path string, onlysn bool) (*obitax.Taxonomy, error) {
+			return func(path string, onlysn, seqAsTaxa bool) (*obitax.Taxonomy, error) {
 				input, err := ReadFastaFromFile(path)
+				input = input.NumberSequences(1, true)
 
 				if err != nil {
 					return nil, err
 				}
 				_, data := input.Load()
 
-				return data.ExtractTaxonomy(nil)
+				return data.ExtractTaxonomy(nil, seqAsTaxa)
 			}, nil
 		case "text/fastq":
-			return func(path string, onlysn bool) (*obitax.Taxonomy, error) {
+			return func(path string, onlysn, seqAsTaxa bool) (*obitax.Taxonomy, error) {
 				input, err := ReadFastqFromFile(path)
+				input = input.NumberSequences(1, true)
 
 				if err != nil {
 					return nil, err
 				}
 				_, data := input.Load()
 
-				return data.ExtractTaxonomy(nil)
+				return data.ExtractTaxonomy(nil, seqAsTaxa)
 			}, nil
 		}
 
@@ -96,14 +98,14 @@ func DetectTaxonomyFormat(path string) (TaxonomyLoader, error) {
 	return nil, nil
 }
 
-func LoadTaxonomy(path string, onlysn bool) (*obitax.Taxonomy, error) {
+func LoadTaxonomy(path string, onlysn, seqAsTaxa bool) (*obitax.Taxonomy, error) {
 	loader, err := DetectTaxonomyFormat(path)
 
 	if err != nil {
 		return nil, err
 	}
 
-	taxonomy, err := loader(path, onlysn)
+	taxonomy, err := loader(path, onlysn, seqAsTaxa)
 
 	return taxonomy, err
 }

pkg/obiformats/universal_read.go

@@ -154,8 +154,7 @@ func ReadSequencesFromFile(filename string,
 	return obiiter.NilIBioSequence, nil
 }
 
-// func ReadSequencesFromStdin(options ...WithOption) obiiter.IBioSequence {
-
-// 	options = append(options, OptionsSource("stdin"))
-
-// }
+func ReadSequencesFromStdin(options ...WithOption) (obiiter.IBioSequence, error) {
+	options = append(options, OptionCloseFile())
+	return ReadSequencesFromFile("-", options...)
+}