Rename obifind obitaxonomy and introduce the new CSV format for taxonomy.

Release-notes.md

@@ -7,6 +7,8 @@
 - In `obimultiplex`, the short version of the **--tag-list** option used to specify the list 
   of tags and primers to be used for the demultiplexing has been changed from `-t` to `-s`.
 
+- The command `obifind` is now renamed `obitaxonomy`.
+
 - The **--taxdump** option used to specify the path to the taxdump containing the NCBI taxonomy
   has been renamed to **--taxonomy**.
 
@@ -21,6 +23,11 @@
 
 ### New features
 
+-   `obitoaxonomy` a new **--dump|D** option allows for dumping a sub-taxonomy.
+  
+-   Taxonomy dump can now be provided as a four-columns CSV file to the **--taxonomy**
+    option.
+
 -   NCBI Taxonomy dump does not need to be uncompressed and unarchived anymore. The
     path of the tar and gziped dump file can be directly specified using the
     **--taxonomy** option.

cmd/obitools/obitaxonomy/main.go

@@ -6,25 +6,29 @@ import (
 
 	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obioptions"
 	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitax"
-	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitools/obifind"
+	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitools/obitaxonomy"
 	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiutils"
 )
 
 func main() {
-	optionParser := obioptions.GenerateOptionParser(obifind.OptionSet)
+	optionParser := obioptions.GenerateOptionParser(obitaxonomy.OptionSet)
 
 	_, args := optionParser(os.Args)
 
 	var iterator *obitax.ITaxon
 
 	switch {
-	case obifind.CLIRequestsPathForTaxid() != "NA":
 
-		taxon := obitax.DefaultTaxonomy().Taxon(obifind.CLIRequestsPathForTaxid())
+	case obitaxonomy.CLIDumpSubtaxonomy():
+		iterator = obitaxonomy.CLISubTaxonomyIterator()
+
+	case obitaxonomy.CLIRequestsPathForTaxid() != "NA":
+
+		taxon := obitax.DefaultTaxonomy().Taxon(obitaxonomy.CLIRequestsPathForTaxid())
 
 		if taxon == nil {
 			log.Fatalf("Cannot identify the requested taxon: %s",
-				obifind.CLIRequestsPathForTaxid())
+				obitaxonomy.CLIRequestsPathForTaxid())
 		}
 
 		s := taxon.Path()
@@ -35,7 +39,7 @@ func main() {
 
 		iterator = s.Iterator()
 
-		if obifind.CLIWithQuery() {
+		if obitaxonomy.CLIWithQuery() {
 			iterator = iterator.AddMetadata("query", taxon.String())
 		}
 
@@ -45,8 +49,8 @@ func main() {
 		iters := make([]*obitax.ITaxon, len(args))
 
 		for i, pat := range args {
-			ii := obitax.DefaultTaxonomy().IFilterOnName(pat, obifind.CLIFixedPattern(), true)
+			ii := obitax.DefaultTaxonomy().IFilterOnName(pat, obitaxonomy.CLIFixedPattern(), true)
-			if obifind.CLIWithQuery() {
+			if obitaxonomy.CLIWithQuery() {
 				ii = ii.AddMetadata("query", pat)
 			}
 			iters[i] = ii
@@ -59,8 +63,8 @@ func main() {
 		}
 	}
 
-	iterator = obifind.CLITaxonRestrictions(iterator)
+	iterator = obitaxonomy.CLITaxonRestrictions(iterator)
-	obifind.CLICSVTaxaWriter(iterator, true)
+	obitaxonomy.CLICSVTaxaWriter(iterator, true)
 
 	obiutils.WaitForLastPipe()
 

pkg/obioptions/version.go

@@ -8,7 +8,7 @@ import (
 // corresponds to the last commit, and not the one when the file will be
 // commited
 
-var _Commit = "7c4042d"
+var _Commit = "c50a0f4"
 var _Version = "Release 4.2.0"
 
 // Version returns the version of the obitools package.

pkg/obitax/csviterator.go

@@ -1,11 +1,10 @@
-package obifind
+package obitax
 
 import (
 	"slices"
 
 	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obidefault"
 	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiitercsv"
-	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obitax"
 )
 
 type __options__ struct {
@@ -192,7 +191,7 @@ func OptionsWithMetadata(values ...string) WithOption {
 	return f
 }
 
-func NewCSVTaxaIterator(iterator *obitax.ITaxon, options ...WithOption) *obiitercsv.ICSVRecord {
+func (iterator *ITaxon) CSVTaxaIterator(options ...WithOption) *obiitercsv.ICSVRecord {
 
 	opt := MakeOptions(options)
 	metakeys := make([]string, 0)

pkg/obitax/csvtaxdump_read.go

@@ -11,6 +11,8 @@ import (
 
 func LoadCSVTaxonomy(path string, onlysn bool) (*Taxonomy, error) {
 
+	log.Infof("Loading taxonomy from csv file: %s", path)
+
 	file, err := obiutils.Ropen(path)
 
 	if err != nil {
@@ -47,7 +49,7 @@ func LoadCSVTaxonomy(path string, onlysn bool) (*Taxonomy, error) {
 			parentColIndex = i
 		case "scientific_name":
 			scientific_nameColIndex = i
-		case "rank":
+		case "taxonomic_rank":
 			rankColIndex = i
 		}
 	}
@@ -70,31 +72,45 @@ func LoadCSVTaxonomy(path string, onlysn bool) (*Taxonomy, error) {
 
 	name := obiutils.RemoveAllExt(path)
 	short := obiutils.Basename(path)
-	taxonomy := NewTaxonomy(name, short, obiutils.AsciiAlphaNumSet)
 
 	line, err := csvfile.Read()
+	if err == nil {
+		parts := strings.Split(line[taxidColIndex], " ")
+		parts = strings.Split(parts[0], ":")
+		if len(parts) > 1 {
+			short = parts[0]
+		}
+	}
 
-	for err != nil {
+	log.Infof("Taxonomy name: %s", name)
+	log.Infof("Taxon code: %s", short)
+
+	taxonomy := NewTaxonomy(name, short, obiutils.AsciiAlphaNumSet)
+
+	root := true
+	var taxon *Taxon
+
+	for err == nil {
 		taxid := line[taxidColIndex]
 		parent := line[parentColIndex]
 		scientific_name := line[scientific_nameColIndex]
 		rank := line[rankColIndex]
 
-		parts := strings.Split(rank, ":")
+		taxon, err = taxonomy.AddTaxon(taxid, parent, rank, root, false)
-
-		rank = parts[0]
-
-		root := len(parts) > 1 && parts[1] == "root"
-
-		taxon, err := taxonomy.AddTaxon(taxid, parent, rank, false, root)
-		taxon.SetName(scientific_name, "scientific name")
 
 		if err != nil {
-			return nil, err
+			log.Fatalf("cannot add taxon %s:  %v", taxid, err)
 		}
 
+		root = false
+
+		taxon.SetName(scientific_name, "scientific name")
+
+		line, err = csvfile.Read()
 	}
 
+	log.Infof("%d Taxa loaded", taxonomy.Len())
+
 	if !taxonomy.HasRoot() {
 		return nil, errors.New("taxonomy file does not contain root node")
 	}

pkg/obitax/csvtaxdump_write.go

@@ -1,11 +1 @@
 package obitax
-
-import (
-	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiitercsv"
-)
-
-func WriteTaxonomyCSV(iterator ITaxon,
-	terminalAction bool, filenames ...string) *obiitercsv.ICSVRecord {
-
-	return nil
-}

pkg/obitax/iterator.go

@@ -2,6 +2,7 @@ package obitax
 
 import (
 	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiutils"
+	log "github.com/sirupsen/logrus"
 )
 
 // ITaxon represents an iterator for traversing Taxon instances.
@@ -189,12 +190,12 @@ func (taxon *Taxon) ISubTaxonomy() *ITaxon {
 	go func() {
 		for i := lpath - 1; i >= 0; i-- {
 			taxon := path.Taxon(i)
-			parents[taxon.Node] = true
 			iter.Push(taxon)
 		}
 
 		pushed := true
 
+		log.Warn(parents)
 		for pushed {
 			itaxo := taxo.Iterator()
 			pushed = false
@@ -215,3 +216,13 @@ func (taxon *Taxon) ISubTaxonomy() *ITaxon {
 
 	return iter
 }
+
+func (taxonomy *Taxonomy) ISubTaxonomy(taxid string) *ITaxon {
+	taxon := taxonomy.Taxon(taxid)
+
+	if taxon == nil {
+		return nil
+	}
+
+	return taxon.ISubTaxonomy()
+}

pkg/obitax/taxonomy.go

@@ -197,7 +197,7 @@ func (taxonomy *Taxonomy) Len() int {
 //   - A pointer to the newly created Taxon instance.
 //   - An error if the taxon cannot be added (e.g., it already exists and replace is false).
 func (taxonomy *Taxonomy) AddTaxon(taxid, parent string, rank string, isRoot bool, replace bool) (*Taxon, error) {
-	taxonomy = taxonomy.OrDefault(false)
+	taxonomy = taxonomy.OrDefault(true)
 
 	parentid, perr := taxonomy.Id(parent)
 	if perr != nil {

pkg/obitools/obitaxonomy/obifind.go

@@ -1,4 +1,4 @@
-package obifind
+package obitaxonomy
 
 import (
 	"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obidefault"
@@ -40,24 +40,34 @@ func CLIFilterRankRestriction(iterator *obitax.ITaxon) *obitax.ITaxon {
 	return iterator
 }
 
+func CLISubTaxonomyIterator() *obitax.ITaxon {
+
+	if CLIDumpSubtaxonomy() {
+		return obitax.DefaultTaxonomy().ISubTaxonomy(CLISubTaxonomyNode())
+	}
+
+	log.Fatalf("No sub-taxonomy specified use the --dump option")
+	return nil
+}
+
 func CLICSVTaxaIterator(iterator *obitax.ITaxon) *obiitercsv.ICSVRecord {
 	if iterator == nil {
 		return nil
 	}
 
-	options := make([]WithOption, 0)
+	options := make([]obitax.WithOption, 0)
 
 	options = append(options,
-		OptionsWithPattern(CLIWithQuery()),
+		obitax.OptionsWithPattern(CLIWithQuery()),
-		OptionsWithParent(CLIWithParent()),
+		obitax.OptionsWithParent(CLIWithParent()),
-		OptionsWithRank(CLIWithRank()),
+		obitax.OptionsWithRank(CLIWithRank()),
-		OptionsWithScientificName(CLIWithScientificName()),
+		obitax.OptionsWithScientificName(CLIWithScientificName()),
-		OptionsWithPath(CLIWithPath()),
+		obitax.OptionsWithPath(CLIWithPath()),
-		OptionsRawTaxid(CLIRawTaxid()),
+		obitax.OptionsRawTaxid(CLIRawTaxid()),
-		OptionsSource(obidefault.SelectedTaxonomy()),
+		obitax.OptionsSource(obidefault.SelectedTaxonomy()),
 	)
 
-	return NewCSVTaxaIterator(iterator, options...)
+	return iterator.CSVTaxaIterator(options...)
 }
 
 func CLICSVTaxaWriter(iterator *obitax.ITaxon, terminalAction bool) *obiitercsv.ICSVRecord {

pkg/obitools/obitaxonomy/options.go

@@ -1,4 +1,4 @@
-package obifind
+package obitaxonomy
 
 import (
 	"fmt"
@@ -16,11 +16,12 @@ var __with_path__ = false
 var __with_query__ = false
 var __without_rank__ = false
 var __without_parent__ = false
-var __with_scientific_name__ = false
+var __without_scientific_name__ = false
 var __raw_taxid__ = false
 var __taxid_path__ = "NA"
 var __taxid_sons__ = "NA"
 var __restrict_rank__ = ""
+var __to_dump__ = ""
 
 func FilterTaxonomyOptionSet(options *getoptions.GetOpt) {
 	options.BoolVar(&__rank_list__, "rank-list", false,
@@ -40,27 +41,35 @@ func OptionSet(options *getoptions.GetOpt) {
 		options.Description("Match taxon names using a fixed pattern, not a regular expression"))
 	options.StringVar(&__taxid_path__, "parents", "NA",
 		options.Alias("p"),
+		options.ArgName("TAXID"),
 		options.Description("Displays every parental tree's information for the provided taxid."))
 	options.StringVar(&__restrict_rank__, "rank", "",
+		options.ArgName("RANK"),
 		options.Description("Restrict to the given taxonomic rank."))
 	options.BoolVar(&__without_parent__, "without-parent", __without_parent__,
-		options.Description("Adds a column containing the parent's taxonid for each displayed taxon."))
+		options.Description("Supress the column containing the parent's taxonid from the output."))
 	options.StringVar(&__taxid_sons__, "sons", "NA",
 		options.Alias("s"),
+		options.ArgName("TAXID"),
 		options.Description("Displays every sons' tree's information for the provided taxid."))
 	options.BoolVar(&__with_path__, "with-path", false,
 		options.Description("Adds a column containing the full path for each displayed taxon."))
 	options.BoolVar(&__without_rank__, "without-rank", __without_rank__,
 		options.Alias("R"),
-		options.Description("Adds a column containing the taxonomic rank for each displayed taxon."))
+		options.Description("Supress the column containing the taxonomic rank from the output."))
 	options.BoolVar(&__with_query__, "with-query", false,
 		options.Alias("P"),
 		options.Description("Adds a column containing query used to filter taxon name for each displayed taxon."))
-	options.BoolVar(&__with_scientific_name__, "with-scientific-name", false,
+	options.BoolVar(&__without_scientific_name__, "without-scientific-name", __without_scientific_name__,
 		options.Alias("S"),
-		options.Description("Adds a column containing the scientific name for each displayed taxon."))
+		options.Description("Supress the column containing the scientific name from the output."))
 	options.BoolVar(&__raw_taxid__, "raw-taxid", false,
 		options.Description("Displays the raw taxid for each displayed taxon."))
+	options.StringVar(&__to_dump__, "dump", __to_dump__,
+		options.Alias("D"),
+		options.ArgName("TAXID"),
+		options.Description("Dump a sub-taxonomy corresponding to the precised clade"),
+	)
 }
 
 func CLITaxonomicalRestrictions() (*obitax.TaxonSet, error) {
@@ -109,7 +118,7 @@ func CLIWithRank() bool {
 }
 
 func CLIWithScientificName() bool {
-	return __with_scientific_name__
+	return !__without_scientific_name__
 }
 
 func CLIRawTaxid() bool {
@@ -127,3 +136,11 @@ func CLIFixedPattern() bool {
 func CLIWithQuery() bool {
 	return __with_query__
 }
+
+func CLIDumpSubtaxonomy() bool {
+	return __to_dump__ != ""
+}
+
+func CLISubTaxonomyNode() string {
+	return __to_dump__
+}