Move test files to subfolders and update pytest's conftest.py (#100)

To solve issue #99 
* move test files to relevant subfolders
* create pytest conftest.py for relevant subfolders
* fix redundant fixtures
* move non-shared fixture to specific file

tests/test_chem_classes.py → tests/class_info/test_chem_classes.py

@@ -2,7 +2,7 @@
 from pathlib import Path
 from nplinker.class_info.chem_classes import MolNetEnhancerResults
 
-from . import DATA_DIR
+from .. import DATA_DIR
 
 
 # TODO:  No such file or directory: 'canopus.tsv'

tests/conftest.py

@@ -1,21 +1,57 @@
 from pathlib import Path
 import shutil
 import pytest
-
+from nplinker.metabolomics.metabolomics import load_spectra
+from nplinker.metabolomics.metabolomics import make_families
+from nplinker.metabolomics.spectrum import Spectrum
+from nplinker.strain_collection import StrainCollection
+from nplinker.strains import Strain
 from nplinker.utils import extract_archive
-
 from . import DATA_DIR
 
+
 def _unpack(archive: Path):
     filepath = DATA_DIR / archive
     outdir = DATA_DIR / filepath.stem
     extract_archive(filepath, outdir)
     return filepath, outdir
 
+
 @pytest.fixture(scope="session", autouse=True)
 def prepare_data():
-    _unpack("ProteoSAFe-METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra.zip")
-    _unpack("ProteoSAFe-FEATURE-BASED-MOLECULAR-NETWORKING-92036537-download_cytoscape_data.zip")
+    _unpack(
+        "ProteoSAFe-METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra.zip"
+    )
+    _unpack(
+        "ProteoSAFe-FEATURE-BASED-MOLECULAR-NETWORKING-92036537-download_cytoscape_data.zip"
+    )
     yield
-    shutil.rmtree(DATA_DIR / "ProteoSAFe-METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra")
-    shutil.rmtree(DATA_DIR / "ProteoSAFe-FEATURE-BASED-MOLECULAR-NETWORKING-92036537-download_cytoscape_data")
+    shutil.rmtree(
+        DATA_DIR /
+        "ProteoSAFe-METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra")
+    shutil.rmtree(
+        DATA_DIR /
+        "ProteoSAFe-FEATURE-BASED-MOLECULAR-NETWORKING-92036537-download_cytoscape_data"
+    )
+
+
+@pytest.fixture
+def spec_dict() -> dict[int, Spectrum]:
+    mgf_file = DATA_DIR / "spectra.mgf"
+    edges_file = DATA_DIR / "edges.pairsinfo"
+    return load_spectra(mgf_file, edges_file)
+
+
+@pytest.fixture
+def collection_from_file() -> StrainCollection:
+    filename = DATA_DIR / "strain_mappings.csv"
+    sut = StrainCollection()
+    sut.add_from_file(filename)
+    return sut
+
+
+@pytest.fixture
+def strain() -> Strain:
+    item = Strain("peter")
+    item.aliases = set(["dieter"])
+    return item

tests/test_aa_pred.py → tests/genomics/test_aa_pred.py

@@ -1,7 +1,7 @@
 import pytest
 from Bio import SeqIO
 from nplinker.genomics.aa_pred import AntiSmash5Record, predict_aa
-from . import DATA_DIR
+from .. import DATA_DIR
 
 
 ANTISMASH_FILE = DATA_DIR / "antismash_v5_GCF_000016425.1_NC_009380.1.region017.gbk"

tests/test_gnps_annotation_loader.py → tests/metabolomics/test_gnps_annotation_loader.py

@@ -4,18 +4,17 @@
 from nplinker.metabolomics.gnps.gnps_annotation_loader import \
     GNPSAnnotationLoader
 from nplinker.metabolomics.spectrum import Spectrum
-from . import DATA_DIR
-from .test_metabolomics import spec_dict
+from .. import DATA_DIR
 
 
 class GNPSAnnotationLoaderBuilder:
     def __init__(self):
         self._file = DATA_DIR / "ProteoSAFe-FEATURE-BASED-MOLECULAR-NETWORKING-92036537-download_cytoscape_data/DB_result/7dc5b46b50d94246a1de12ef485d0f75.tsv"
-    
+
     def with_file(self, file) -> Self:
         self._file = file
         return self
-    
+
     def build(self) -> GNPSAnnotationLoader:
         return GNPSAnnotationLoader(self._file)
 
@@ -51,9 +50,9 @@ def test_annotations_are_equal(spec_dict: dict[int, Spectrum]):
             expected[x.spectrum_id] = x.gnps_annotations
 
     actual = GNPSAnnotationLoaderBuilder().with_file(annotations_file).build().get_annotations()
-    
+
     for key in expected:
         expected_annotations = expected[key]
         actual_annotations = actual[key]
         for key_entry in expected_annotations:
-            assert expected_annotations[key_entry] == actual_annotations[key_entry] 
+            assert expected_annotations[key_entry] == actual_annotations[key_entry]

tests/test_gnps_downloader.py → tests/metabolomics/test_gnps_downloader.py

@@ -6,25 +6,25 @@
 
 import pytest
 from nplinker.metabolomics.gnps.gnps_downloader import GNPSDownloader
-from . import DATA_DIR
+from .. import DATA_DIR
 
 
 class GNPSDownloaderBuilder:
     def __init__(self):
         self._task_id = None
         self._download_root = gettempdir()
-    
+
     def with_task_id(self, task_id: str) -> Self:
         self._task_id = task_id
         return self
 
     def with_download_root(self, download_root: Path) -> Self:
         self._download_root = download_root
         return self
-    
+
     def build(self) -> GNPSDownloader:
         return GNPSDownloader(self._task_id, self._download_root)
-    
+
 
 
 def test_has_gnps_task_id():
@@ -51,4 +51,4 @@ def test_downloads_file(tmp_path: Path, task_id, filename_expected):
 
     actual_names = actual.namelist()
     expected_names = [x.filename for x in expected.filelist if x.compress_size > 0]
-    assert all(item in actual_names for item in expected_names)
+    assert all(item in actual_names for item in expected_names)

tests/test_gnps_extractor.py → tests/metabolomics/test_gnps_extractor.py

@@ -8,7 +8,7 @@
 import pytest
 from nplinker.metabolomics.gnps.gnps_extractor import GNPSExtractor
 from nplinker.utils import extract_archive
-from . import DATA_DIR
+from .. import DATA_DIR
 
 
 class GNPSExtractorBuilder:
@@ -24,7 +24,7 @@ def with_file(self, file: Path) -> Self:
     def with_extract_path(self, extract_path: Path) -> Self:
         self._extract_path = extract_path
         return self
-    
+
     def build(self) -> GNPSExtractor:
         return GNPSExtractor(self._file, self._extract_path)
 
@@ -41,7 +41,7 @@ def _unpack(archive: Path):
     extract_archive(file, outdir)
     return file, outdir
 
-    
+
 def test_default():
     sut = GNPSExtractorBuilder().build()
     assert sut is not None
@@ -51,7 +51,7 @@ def test_has_zipfile():
     file = DATA_DIR / 'ProteoSAFe-METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra.zip'
     sut = GNPSExtractorBuilder().with_file(file).build()
     actual = sut.get_data()
-    
+
     expected = zipfile.ZipFile(file)
     numpy.testing.assert_array_equal(actual.namelist(), expected.namelist())
 
@@ -86,7 +86,7 @@ def test_creates_molecular_families(archive: Path, filename: str, tmp_path: Path
     sut = GNPSExtractorBuilder().with_file(file).with_extract_path(tmp_path).build()
     sut._extract_molecular_families()
     actual = Path(sut.get_extract_path()) / "molecular_families.pairsinfo"
-    
+
     assert_extraction_success(filename, outdir, actual)
 
 
@@ -100,7 +100,7 @@ def test_creates_file_mappings(archive: Path, filename: str, tmp_path: Path):
     sut = GNPSExtractorBuilder().with_file(file).with_extract_path(tmp_path).build()
     sut._extract_file_mappings()
     actual = Path(sut.get_extract_path()) / ("file_mappings" + str(Path(filename).suffix))
-    
+
     assert_extraction_success(filename, outdir, actual)
 
 
@@ -113,5 +113,5 @@ def test_creates_annotations(archive: Path, filename: str, tmp_path: Path):
 
     sut = GNPSExtractorBuilder().with_file(file).with_extract_path(tmp_path).build()
     sut._extract_annotations()
-    actual = Path(sut.get_extract_path()) / "annotations.tsv" 
-    assert_extraction_success(filename, outdir, actual)
+    actual = Path(sut.get_extract_path()) / "annotations.tsv"
+    assert_extraction_success(filename, outdir, actual)

tests/test_gnps_format.py → tests/metabolomics/test_gnps_format.py

@@ -5,7 +5,7 @@
 from nplinker.metabolomics.gnps.gnps_format import gnps_format_from_file_mapping
 from nplinker.metabolomics.gnps.gnps_format import gnps_format_from_task_id
 from nplinker.metabolomics.gnps.gnps_format import gnps_format_from_archive
-from . import DATA_DIR
+from .. import DATA_DIR
 
 
 @pytest.mark.parametrize("filename, expected", [

tests/test_gnps_molecular_family_loader.py → tests/metabolomics/test_gnps_molecular_family_loader.py

@@ -1,19 +1,16 @@
 import os
 import numpy
-
 import pytest
-from nplinker.metabolomics.gnps.gnps_molecular_family_loader import GNPSMolecularFamilyLoader
+from nplinker.metabolomics.gnps.gnps_molecular_family_loader import \
+    GNPSMolecularFamilyLoader
+from nplinker.metabolomics.metabolomics import make_families
 from nplinker.metabolomics.molecular_family import MolecularFamily
+from .. import DATA_DIR
 
-from .test_metabolomics import molecular_families, spec_dict
-from . import DATA_DIR
 
 @pytest.fixture
-def molecular_families_gnps():
-    filename = os.path.join(DATA_DIR, "edges.pairsinfo")
-    sut = GNPSMolecularFamilyLoader(filename)
-    return sut.families()
-
+def molecular_families(spec_dict) -> list[MolecularFamily]:
+    return make_families(spec_dict.values())
 
 @pytest.mark.parametrize("filename", [
     os.path.join(DATA_DIR, "edges.pairsinfo"),
@@ -36,10 +33,10 @@ def test_families_are_identical(spec_dict, molecular_families):
         x.id = i
         for spec_id in x.spectra_ids:
             x.add_spectrum(spec_dict[spec_id])
-            
+
 
     for x in molecular_families:
         for spec in x.spectra:
             x.spectra_ids.add(spec.spectrum_id)
 
-    numpy.testing.assert_array_equal(actual, molecular_families)
+    numpy.testing.assert_array_equal(actual, molecular_families)

tests/test_gnps_spectrum_loader.py → tests/metabolomics/test_gnps_spectrum_loader.py

@@ -1,12 +1,12 @@
 import pytest
 from nplinker.metabolomics.gnps.gnps_spectrum_loader import GNPSSpectrumLoader
 
-from . import DATA_DIR
+from .. import DATA_DIR
 
 @pytest.mark.parametrize("file, expected", [
     [DATA_DIR / "ProteoSAFe-METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra/METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra-main.mgf", 435],
     [DATA_DIR / "ProteoSAFe-FEATURE-BASED-MOLECULAR-NETWORKING-92036537-download_cytoscape_data/spectra/specs_ms.mgf", 1492]
 ])
 def test_loads_spectra(file, expected):
     actual = GNPSSpectrumLoader(file).spectra()
-    assert len(actual) == expected
+    assert len(actual) == expected

tests/test_load_gnps.py → tests/metabolomics/test_load_gnps.py

@@ -7,10 +7,8 @@
 from nplinker.metabolomics.load_gnps import load_gnps
 from nplinker.strain_collection import StrainCollection
 from nplinker.utils import get_headers
-from .test_metabolomics import spec_dict
-from .test_strain_collection import collection_from_file
 
-from . import DATA_DIR
+from .. import DATA_DIR
 
 
 nodes_file = DATA_DIR / "nodes.tsv"
@@ -77,4 +75,4 @@ def test_parse_mzxml_header():
     headers = get_headers(str(DATA_DIR / "nodes_fbmn.csv"))
     hdr = headers[10]
     actual = _parse_mzxml_header(hdr, StrainCollection(), None, None)
-    assert actual is not None
+    assert actual is not None

tests/test_metabolomics.py → tests/metabolomics/test_metabolomics.py

@@ -1,27 +1,7 @@
-import pytest
 from nplinker.metabolomics.metabolomics import make_families
 from nplinker.metabolomics.metabolomics import load_dataset
-from nplinker.metabolomics.metabolomics import load_spectra
-from nplinker.metabolomics.molecular_family import MolecularFamily
-from nplinker.metabolomics.spectrum import Spectrum
 from nplinker.strain_collection import StrainCollection
-from . import DATA_DIR
-
-
-@pytest.fixture
-def spec_dict() -> dict[int, Spectrum]:
-    mgf_file = DATA_DIR / "spectra.mgf"
-    edges_file = DATA_DIR / "edges.pairsinfo"
-    return load_spectra(mgf_file, edges_file)
-
-@pytest.fixture
-def spec_with_families(spec_dict) -> dict[int, Spectrum]:
-    make_families(spec_dict.values())
-    return spec_dict
-
-@pytest.fixture
-def molecular_families(spec_dict) -> list[MolecularFamily]:
-    return make_families(spec_dict.values())
+from .. import DATA_DIR
 
 
 def test_load_spectra(spec_dict):
@@ -47,4 +27,4 @@ def test_load_dataset():
 
 def test_make_families(spec_dict):
     families = make_families(spec_dict.values())
-    assert len(families) == 25769
+    assert len(families) == 25769

tests/test_downloader.py → tests/pairedomics/test_downloader.py

@@ -10,7 +10,7 @@
 from nplinker.pairedomics.downloader import Downloader
 from nplinker.pairedomics.downloader import _generate_gnps_download_url
 from nplinker.pairedomics.downloader import _execute_download
-from . import DATA_DIR
+from .. import DATA_DIR
 
 
 @pytest.fixture
@@ -80,7 +80,7 @@ def test_download_gnps_data(tmp_path):
     gnps_task_id = "c22f44b14a3d450eb836d607cb9521bb"
     sut = Downloader("MSV000079284", local_cache=tmp_path / 'actual')
     actual = sut._load_gnps_data(gnps_task_id)
-    
+
     expected = zipfile.ZipFile(DATA_DIR / "ProteoSAFe-METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra.zip")
 
     actual.extract("networkedges_selfloop/6da5be36f5b14e878860167fa07004d6.pairsinfo", tmp_path / "actual")
@@ -101,4 +101,3 @@ def test_extract_metabolomics_data(tmp_path):
     assert (Path(sut.project_file_cache) / "networkedges_selfloop/6da5be36f5b14e878860167fa07004d6.pairsinfo").is_file()
     assert (Path(sut.project_file_cache) / "clusterinfosummarygroup_attributes_withIDs_withcomponentID/d69356c8e5044c2a9fef3dd2a2f991e1.tsv").is_file()
     assert (Path(sut.project_file_cache) / "spectra/METABOLOMICS-SNETS-c22f44b1-download_clustered_spectra-main.mgf").is_file()
-

tests/test_mgf.py → tests/parsers/test_mgf.py

@@ -1,6 +1,6 @@
 from nplinker.parsers.mgf import LoadMGF
 
-from . import DATA_DIR
+from .. import DATA_DIR
 
 
 def test_load_mgf():