Add (a)cellular root ranks

.github/workflows/test_ncbi.yml

@@ -0,0 +1,41 @@
+name: Test Latest NCBI Taxonomy
+on:
+  push:
+    branches:
+      - master
+  pull_request:
+  schedule:
+    - cron: '0 0 1 * *' # runs at 00:00 on the 1st of every month (UTC)
+
+jobs:
+  test-ncbi-python-bindings:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - uses: actions-rs/toolchain@v1
+        with:
+          profile: minimal
+          toolchain: stable
+          override: true
+
+      - name: Install python headers
+        run: sudo apt-get update && sudo apt-get install python3-dev python3-pip python3-venv
+
+      - name: Install python dependencies
+        run: |
+          python3 -m venv venv
+          . venv/bin/activate
+          pip3 install maturin downloads
+          pip3 show maturin
+
+      - name: Add library to venv
+        run: |
+          . venv/bin/activate
+          maturin develop --features=python
+
+      - name: Test Python bindings with latest NCBI taxonomy
+        run: |
+          . venv/bin/activate
+          TAXONOMY_TEST_NCBI=true python -m unittest test_python.LatestNCBITestCase.test_load_latest_ncbi_taxonomy

.github/workflows/tests.yml

@@ -49,7 +49,7 @@ jobs:
         run: |
           python3 -m venv venv
           . venv/bin/activate
-          pip3 install maturin
+          pip3 install maturin downloads
           pip3 show maturin
 
       - name: add library to venv

src/rank.rs

@@ -15,6 +15,8 @@ use crate::errors::{Error, ErrorKind, TaxonomyResult};
 #[non_exhaustive]
 pub enum TaxRank {
     Domain,
+    AcellularRoot,
+    CellularRoot,
     Subdomain,
     Realm,
     Subrealm,
@@ -113,6 +115,8 @@ impl TaxRank {
     pub fn to_ncbi_rank(self) -> &'static str {
         match self {
             TaxRank::Superkingdom => "superkingdom",
+            TaxRank::AcellularRoot => "acellular root",
+            TaxRank::CellularRoot => "cellular root",
             TaxRank::Kingdom => "kingdom",
             TaxRank::Subkingdom => "subkingdom",
             TaxRank::Superphylum => "superphylum",
@@ -170,6 +174,8 @@ impl FromStr for TaxRank {
             "domain" | "regio" => Ok(TaxRank::Domain),
             "subdomain" => Ok(TaxRank::Subdomain),
             "realm" => Ok(TaxRank::Realm),
+            "acellular root" => Ok(TaxRank::AcellularRoot),
+            "cellular root" => Ok(TaxRank::CellularRoot),
             "subrealm" => Ok(TaxRank::Subrealm),
             "hyperkingdom" | "hyperregnum" => Ok(TaxRank::Hyperkingdom),
             "superkingdom" | "superregnum" => Ok(TaxRank::Superkingdom),
@@ -257,6 +263,8 @@ impl fmt::Display for TaxRank {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
         let rank_str = match self {
             TaxRank::Domain => "domain",
+            TaxRank::AcellularRoot => "acellular root",
+            TaxRank::CellularRoot => "cellular root",
             TaxRank::Subdomain => "subdomain",
             TaxRank::Realm => "realm",
             TaxRank::Subrealm => "subrealm",
@@ -357,6 +365,7 @@ mod test {
 
     static RANKS: &[super::TaxRank] = &[
         Domain,
+        AcellularRoot,
         Subdomain,
         Realm,
         Subrealm,

test_python.py

@@ -2,6 +2,9 @@
 import unittest
 
 from taxonomy import Taxonomy, TaxonomyError
+from downloads import download
+import os
+import subprocess
 
 JSON_DATA = """
 {
@@ -487,5 +490,15 @@ def test_invalid_format(self):
                 Taxonomy.from_gtdb(file.read())
 
 
+class LatestNCBITestCase(unittest.TestCase):
+    @unittest.skipUnless(
+        os.getenv("TAXONOMY_TEST_NCBI"), "Define TAXONOMY_TEST_NCBI to run NCBI test"
+    )
+    def test_load_latest_ncbi_taxonomy(self):
+        download("https://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz")
+        subprocess.check_output(["tar", "-zxvf", "taxdump.tar.gz"])
+        Taxonomy.from_ncbi(".")
+
+
 if __name__ == "__main__":
     unittest.main()

tests/data/nodes.dmp

@@ -1,10 +1,10 @@
 1	|	1	|	no rank	|		|	8	|	0	|	1	|	0	|	0	|	0	|	0	|	0	|		|
-10239	|	1	|	no_rank	|		|	9	|	0	|	1	|	0	|	0	|	0	|	0	|	0	|		|
+10239	|	1	|	acellular root	|		|	9	|	0	|	1	|	0	|	0	|	0	|	0	|	0	|		|
 2	|	131567	|	superkingdom	|		|	0	|	0	|	11	|	0	|	0	|	0	|	0	|	0	|		|
 543	|	91347	|	family	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|
 561	|	543	|	genus	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|
 562	|	561	|	species	|	EC	|	0	|	1	|	11	|	1	|	0	|	1	|	1	|	0	|		|
 1224	|	2	|	phylum	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|
 1236	|	1224	|	class	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|
 91347	|	1236	|	order	|		|	0	|	1	|	11	|	1	|	0	|	1	|	0	|	0	|		|
-131567	|	1	|	no rank	|		|	8	|	1	|	1	|	1	|	0	|	1	|	1	|	0	|		|
+131567	|	1	|	cellular root	|		|	8	|	1	|	1	|	1	|	0	|	1	|	1	|	0	|		|