lingyuzeng
5e7b236f31
Unify macrolactone detection, numbering, fragmentation, and splicing under the installable macro_lactone_toolkit package. - replace legacy src.* modules with the new package layout - add analyze/number/fragment CLI entrypoints and pixi tasks - migrate tests, README, and scripts to the new package API
75 lines
2.3 KiB
Python
75 lines
2.3 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
import subprocess
|
|
import sys
|
|
|
|
import pandas as pd
|
|
|
|
from .helpers import build_ambiguous_smiles, build_macrolactone
|
|
|
|
|
|
def run_cli(*args: str) -> subprocess.CompletedProcess[str]:
|
|
return subprocess.run(
|
|
[sys.executable, "-m", "macro_lactone_toolkit.cli", *args],
|
|
capture_output=True,
|
|
text=True,
|
|
check=False,
|
|
)
|
|
|
|
|
|
def test_cli_smoke_commands():
|
|
built = build_macrolactone(16, {5: "methyl"})
|
|
|
|
analyze = run_cli("analyze", "--smiles", built.smiles)
|
|
assert analyze.returncode == 0, analyze.stderr
|
|
analyze_payload = json.loads(analyze.stdout)
|
|
assert analyze_payload["valid_ring_sizes"] == [16]
|
|
|
|
number = run_cli("number", "--smiles", built.smiles)
|
|
assert number.returncode == 0, number.stderr
|
|
number_payload = json.loads(number.stdout)
|
|
assert number_payload["ring_size"] == 16
|
|
assert number_payload["position_to_atom"]["1"] >= 0
|
|
|
|
fragment = run_cli("fragment", "--smiles", built.smiles, "--parent-id", "cli_1")
|
|
assert fragment.returncode == 0, fragment.stderr
|
|
fragment_payload = json.loads(fragment.stdout)
|
|
assert fragment_payload["parent_id"] == "cli_1"
|
|
assert fragment_payload["ring_size"] == 16
|
|
assert fragment_payload["fragments"][0]["fragment_smiles_labeled"]
|
|
|
|
|
|
def test_cli_fragment_csv_skips_ambiguous_and_records_errors(tmp_path):
|
|
valid = build_macrolactone(14, {4: "methyl"})
|
|
ambiguous = build_ambiguous_smiles()
|
|
input_path = tmp_path / "molecules.csv"
|
|
output_path = tmp_path / "fragments.csv"
|
|
errors_path = tmp_path / "errors.csv"
|
|
|
|
pd.DataFrame(
|
|
[
|
|
{"id": "valid_1", "smiles": valid.smiles},
|
|
{"id": "ambiguous_1", "smiles": ambiguous},
|
|
]
|
|
).to_csv(input_path, index=False)
|
|
|
|
completed = run_cli(
|
|
"fragment",
|
|
"--input",
|
|
str(input_path),
|
|
"--output",
|
|
str(output_path),
|
|
"--errors-output",
|
|
str(errors_path),
|
|
)
|
|
|
|
assert completed.returncode == 0, completed.stderr
|
|
|
|
fragments = pd.read_csv(output_path)
|
|
errors = pd.read_csv(errors_path)
|
|
|
|
assert set(fragments["parent_id"]) == {"valid_1"}
|
|
assert errors.loc[0, "parent_id"] == "ambiguous_1"
|
|
assert errors.loc[0, "error_type"] == "AmbiguousMacrolactoneError"
|