allow from-nhx cli to set species encode way (#25)

README.md

@@ -215,19 +215,26 @@ orthoxml-tools to-nhx --infile examples/data/sample-for-nhx.orthoxml --outdir ./
 Convert Newick (NHX) format to OrthoXML.
 
 ```bash
-orthoxml-tools from-nhx --infile path/to/file.nhx --outfile path/to/file.orthoxml
+orthoxml-tools from-nhx --infile path/to/file.nhx --outfile path/to/file.orthoxml [--species-encode nhx|underscore]
 ```
 
 **Options:**
 - `--infile <file>`: Specify the input nhx file or files. (at least one file is required).
   - You can specify multiple files by providing them as a space-separated list.
   - If you provide multiple files, they will be combined into a single OrthoXML output.
 - `--outfile <folder>`: Specify the output OrthoXML file (required).
+- `--species-encode <nhx|underscore>`: How species/taxonomic levels are encoded in the Newick files.
+    nhx → Species encoded in NHX comments using S= or T= tags. For example: (A_s1:0.1[&&NHX:conf=0.9:S=s1],B_s2:0.2[&&NHX:conf=0.8:S=s2]);
+    underscore → Species encoded in leaf labels using underscores (e.g., GeneID_SpeciesID).
 
 **Example:**
 ```bash
 orthoxml-tools from-nhx --infile examples/data/sample.nhx --outfile ./tests_output/from_nhx.orthoxml
 orthoxml-tools from-nhx --infile examples/data/sample2.nhx examples/data/sample.nhx --outfile ./tests_output/from_nhx21.orthoxml 
+orthoxml-tools from-nhx \
+  --species-encode nhx \
+  --infile examples/data/sample.nhx \
+  --outfile tests_output/from_nhx_nhxspecies.orthoxml
 ```
 
 ### 🛠️ CSV to OrthoXML (exploratory feature)

examples/data/sample.nhx

@@ -1 +1 @@
-((A_s1:0.1[&&NHX:conf=0.9],B_s2:0.2[&&NHX:conf=0.8])[&&NHX:S=speciesA],C_s3:0.3[&&NHX:S=speciesB]);
+((A_s1:0.1[&&NHX:conf=0.9:S=s1],B_s2:0.2[&&NHX:conf=0.8:S=s2])[&&NHX:S=speciesA],C_s3:0.3[&&NHX:S=speciesB]);

src/orthoxml/cli.py

@@ -8,7 +8,7 @@
 from orthoxml import __version__
 from orthoxml.parsers import process_stream_orthoxml
 from orthoxml.converters.to_nhx import orthoxml_to_newick
-from orthoxml.converters.from_nhx import orthoxml_from_newicktrees
+from orthoxml.converters.from_nhx import (orthoxml_from_newicktrees, nhx_species_encoded_leaf)
 from orthoxml.converters.from_orthofinder import convert_csv_to_orthoxml
 from orthoxml.custom_parsers import (
     BasicStats,
@@ -178,11 +178,15 @@ def handle_conversion_to_nhx(args):
     logger.info("You can visualise each tree using https://beta.phylo.io/viewer/ as extended newick format.")
 
 def handle_conversion_from_nhx(args):
+    if args.species_encode == "nhx":
+        species_encode = nhx_species_encoded_leaf
+    else:
+        species_encode = None
     orthoxml_from_newicktrees(
         args.infile,
         args.outfile,
         label_to_event=None, 
-        label_to_id_and_species=None
+        label_to_id_and_species=species_encode
     )
 
 def handle_conversion_from_orthofinder(args):
@@ -277,6 +281,13 @@ def main():
         required=True,
         help="Paths to one or more Newick (NHX) files"
     )
+    converter_from_nhx_parser.add_argument(
+        "--species-encode",
+        required=False,
+        choices=("nhx", "underscore"),
+        help="Way how species/taxonomic levels are encoded in the input Newick files. 'nhx' means that the "
+             "species/taxonomic levels are encoded in the Newick file using the NHX comments S= or T=, 'underscore' "
+             "means that the species/taxonomic levels are encoded in the Newick file using underscores.")
     converter_from_nhx_parser.add_argument("--outfile", required=True, help="Path to the output OrthoXML file")
     converter_from_nhx_parser.set_defaults(func=handle_conversion_from_nhx)
 

tests/test_cli.sh

@@ -81,6 +81,8 @@ orthoxml-tools to-nhx \
 echo -e "\n[10] Test: Newick (NHX) to OrthoXML conversion"
 orthoxml-tools from-nhx --infile "$EXAMPLES_DIR/sample.nhx" --outfile "tests_output/from_nhx.orthoxml"
 orthoxml-tools from-nhx --infile "$EXAMPLES_DIR/sample2.nhx" "$EXAMPLES_DIR/sample.nhx" --outfile "tests_output/from_nhx21.orthoxml"
+orthoxml-tools from-nhx --species-encode "nhx" --infile "$EXAMPLES_DIR/sample.nhx" --outfile "tests_output/from_nhx_nhxspecies.orthoxml"
+
 
 echo -e "\n[11] Test: Orthofinder CSV to OrthoXML conversion"
 orthoxml-tools from-csv --infile examples/data/InputOrthogroups.csv --outfile tests_output/orthofinder.orthoxml