Aurora-MCP

import sys from pathlib import Path import pandas as pd import pytest ROOT = Path(__file__).resolve().parents[1] if str(ROOT) not in sys.path: sys.path.insert(0, str(ROOT)) from mcp_server.datasets import DatasetLoadError, LoadedDataset # noqa: E402 from mcp_server.links import link_compound_to_nordic_plants # noqa: E402 def test_link_compound_to_nordic_plants_merges_records(monkeypatch): compound = "Arctigenin" coconut_df = pd.DataFrame( { "name": ["arctigenin"], "organisms": ["Arctium lappa|Rosa canina"], } ) laji_df = pd.DataFrame( { "Scientific name": ["Arctium lappa", "Rosa canina"], "Observation count from Finland": [1200, 900], "Identifier": ["MX.123", "MX.456"], } ) gbif_df = pd.DataFrame( { "canonicalName": ["arctium lappa", "rosa canina"], "speciesKey": [12345, 67890], "obs_FI": [1500, 1100], "obs_NO": [200, 150], "count_FI_60N": [400, 300], "count_NO_60N": [50, 40], "count_FI_66N": [20, 10], "count_NO_66N": [5, 3], } ) dataset_map = { "coconut_csv-09-2025_FI_NO_plants.csv": coconut_df, "laji2_fi.txt": laji_df, "gbif_plants_FI_NO_merged.tsv": gbif_df, } def fake_load_dataset(name: str): if name not in dataset_map: raise DatasetLoadError(f"missing dataset {name}") return LoadedDataset(name=name, frame=dataset_map[name].copy(), source_path=Path(name), metadata={}) monkeypatch.setattr("mcp_server.links.load_dataset", fake_load_dataset) result = link_compound_to_nordic_plants(compound) assert result["compound"].lower() == "arctigenin" assert sorted(result["organisms"]) == ["Arctium lappa", "Rosa canina"] rows = {row["organism"]: row for row in result["table"]} assert rows["Arctium lappa"]["obs_FI_laji"] == 1200 assert rows["Arctium lappa"]["obs_FI_gbif"] == 1500 assert rows["Arctium lappa"]["url_laji"].endswith("MX.123/occurrence") assert rows["Arctium lappa"]["url_gbif"].endswith("/12345") assert rows["Rosa canina"]["obs_NO_gbif"] == 150 assert result["missing_in_laji"] == [] assert result["missing_in_gbif"] == [] def test_link_compound_to_nordic_plants_missing_compound(monkeypatch): coconut_df = pd.DataFrame({"name": ["arctigenin"], "organisms": ["Arctium lappa"]}) dataset_map = { "coconut_csv-09-2025_FI_NO_plants.csv": coconut_df, "laji2_fi.txt": pd.DataFrame(columns=["Scientific name", "Observation count from Finland", "Identifier"]), "gbif_plants_FI_NO_merged.tsv": pd.DataFrame( columns=["canonicalName", "speciesKey", "obs_FI", "obs_NO", "count_FI_60N", "count_NO_60N", "count_FI_66N", "count_NO_66N"] ), } def fake_load_dataset(name: str): return LoadedDataset(name=name, frame=dataset_map[name].copy(), source_path=Path(name), metadata={}) monkeypatch.setattr("mcp_server.links.load_dataset", fake_load_dataset) result = link_compound_to_nordic_plants("unknown") assert result["organisms"] == [] assert result["table"] == []