Renaming project to NSBDiagnosisToolkit

src/nsbdiagnosistoolkit/cli/aggregator.py

@@ -0,0 +1,23 @@
+from os import path
+from typing import Any, AsyncGenerator, AsyncIterable, Iterable, Sequence
+from nsbdiagnosistoolkit.engine.data.MLST import MLSTProfile
+from nsbdiagnosistoolkit.engine.data.genomics import NamedString
+from nsbdiagnosistoolkit.engine.local.abif import read_abif
+from nsbdiagnosistoolkit.engine.local.fasta import read_fasta
+from nsbdiagnosistoolkit.engine.remote.databases.institutpasteur.profiling import InstitutPasteurProfiler
+
+
+async def aggregate_sequences(fastas: Iterable[str], abifs: Iterable[str]) -> AsyncGenerator[str, Any]:
+    for fasta_path in fastas:
+        async for fasta in read_fasta(fasta_path):
+            yield fasta.sequence
+    for abif_path in abifs:
+        abif_data = await read_abif(abif_path)
+        yield "".join(abif_data.sequence)
+
+async def profile_all_genetic_strings(strings: AsyncIterable[str], database_name: str) -> Sequence[MLSTProfile]:
+    profiles = list()
+    async with InstitutPasteurProfiler(database_name=database_name) as profiler:
+        async for string in strings:
+            profiles.append(await profiler.profile_string(string))
+    return profiles

src/nsbdiagnosistoolkit/cli/program.py

@@ -0,0 +1,58 @@
+import argparse
+import asyncio
+from os import path
+
+from nsbdiagnosistoolkit.cli import aggregator
+from nsbdiagnosistoolkit.engine.data.genomics import NamedString
+from nsbdiagnosistoolkit.engine.local.abif import read_abif
+from nsbdiagnosistoolkit.engine.local.csv import write_mlst_profiles_as_csv
+from nsbdiagnosistoolkit.engine.local.fasta import read_fasta
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument(
+    "--fasta", "-fa", "-fst",
+    nargs="+",
+    action='extend',
+    dest="fastas",
+    required=False,
+    default=[],
+    type=str,
+    help="The FASTA files to process. Multiple can be listed."
+)
+parser.add_argument(
+    "--abif", "-abi", "-ab1",
+    action='extend',
+    dest="abifs",
+    required=False,
+    default=[],
+    type=str,
+    help="The ABIF files to process. Multiple can be listed."
+)
+parser.add_argument(
+    "--institut-pasteur-mlst",
+    "-ipdbmlst",
+    dest="institut_pasteur_db",
+    type=str,
+    help="The Institut Pasteur MLST database to use."
+)
+parser.add_argument(
+    "-csv",
+    dest="csv_path",
+    required=False,
+    default=None,
+    help="The destination to place the CSV output."
+)
+
+
+def cli():
+    args = parser.parse_args()
+    gen_strings = aggregator.aggregate_sequences(args.fastas, args.abifs)
+    mlst_profiles = aggregator.profile_all_genetic_strings(
+        gen_strings, args.institut_pasteur_db)
+    asyncio.run(write_mlst_profiles_as_csv(
+        asyncio.run(mlst_profiles), str(args.csv_path)))
+
+
+if __name__ == "__main__":
+    cli()