Merge pull request #1150 from khushthecoder/GH1108-plasmodium-truthiness-bug

Fix #1108: Replace truthiness checks with explicit None checks in gen…

Author: jonbrenas

malariagen_data/anoph/genome_sequence.py

@@ -117,9 +117,13 @@ def genome_sequence(
 
         # Deal with region start and stop.
         slice_start = slice_stop = None
-        if resolved_region.start:
+        if resolved_region.start is not None:
+            if resolved_region.start < 1:
+                raise ValueError("Region start must be >= 1 or None.")
             slice_start = resolved_region.start - 1
-        if resolved_region.end:
+        if resolved_region.end is not None:
+            if resolved_region.end < 1:
+                raise ValueError("Region end must be >= 1 or None.")
             slice_stop = resolved_region.end
         loc_region = slice(slice_start, slice_stop)
 

malariagen_data/anoph/snp_data.py

@@ -1719,7 +1719,7 @@ def is_accessible(
 
         # Access SNP site positions.
         pos = self.snp_sites(region=resolved_region, field="POS").compute()
-        if resolved_region.start:
+        if resolved_region.start is not None:
             offset = resolved_region.start
         else:
             offset = 1

malariagen_data/anoph/snp_frq.py

@@ -671,8 +671,10 @@ def snp_allele_frequencies_advanced(
 
             # Check for no SNPs remaining after applying variant query.
             if np.count_nonzero(loc_variants) == 0:
-                raise ValueError(
-                    f"No SNPs remaining after applying variant query {variant_query!r}."
+                warnings.warn(
+                    f"No SNPs remaining after applying variant query {variant_query!r}. "
+                    "Returning dataset with zero variants.",
+                    stacklevel=2,
                 )
 
             # Convert boolean mask to integer indices for NumPy 2.x compatibility
@@ -813,8 +815,10 @@ def aa_allele_frequencies_advanced(
 
             # Check for no SNPs remaining after applying variant query.
             if np.count_nonzero(loc_variants) == 0:
-                raise ValueError(
-                    f"No SNPs remaining after applying variant query {variant_query!r}."
+                warnings.warn(
+                    f"No SNPs remaining after applying variant query {variant_query!r}. "
+                    "Returning dataset with zero variants.",
+                    stacklevel=2,
                 )
 
             # Convert boolean mask to integer indices for NumPy 2.x compatibility

tests/anoph/test_genome_sequence.py

@@ -9,6 +9,7 @@
 from malariagen_data import af1 as _af1
 from malariagen_data import ag3 as _ag3
 from malariagen_data.anoph.genome_sequence import AnophelesGenomeSequenceData
+from malariagen_data.util import Region
 
 
 @pytest.fixture
@@ -123,5 +124,14 @@ def test_genome_sequence_virtual_contigs(ag3_sim_api, chrom):
     seq_region = api.genome_sequence(region=region)
     assert isinstance(seq_region, da.Array)
     assert seq_region.ndim == 1
-    assert seq_region.dtype == seq.dtype
     assert seq_region.shape[0] == stop - start + 1
+
+
+@parametrize_with_cases("fixture,api", cases=".")
+def test_genome_sequence_invalid_region(fixture, api):
+    for contig in fixture.contigs:
+        with pytest.raises(ValueError, match="Region start must be >= 1 or None."):
+            api.genome_sequence(region=Region(contig, start=0, end=100))
+
+        with pytest.raises(ValueError, match="Region end must be >= 1 or None."):
+            api.genome_sequence(region=Region(contig, start=1, end=0))

tests/anoph/test_snp_frq.py

@@ -1520,24 +1520,29 @@ def test_allele_frequencies_advanced_with_variant_query(
         variant_query=variant_query,
     )
 
-    # Test a query that should fail.
+    # Test a query that should warn and return empty.
     variant_query = "effect == 'foobar'"
-    with pytest.raises(ValueError):
-        api.snp_allele_frequencies_advanced(
+    with pytest.warns(UserWarning):
+        ds_snp = api.snp_allele_frequencies_advanced(
             transcript=transcript,
             sample_sets=all_sample_sets,
             area_by=area_by,
             period_by=period_by,
             variant_query=variant_query,
+            min_cohort_size=0,
         )
-    with pytest.raises(ValueError):
-        api.aa_allele_frequencies_advanced(
+        assert ds_snp.sizes["variants"] == 0
+
+    with pytest.warns(UserWarning):
+        ds_aa = api.aa_allele_frequencies_advanced(
             transcript=transcript,
             sample_sets=all_sample_sets,
             area_by=area_by,
             period_by=period_by,
             variant_query=variant_query,
+            min_cohort_size=0,
         )
+        assert ds_aa.sizes["variants"] == 0
 
 
 @pytest.mark.parametrize("nobs_mode", ["called", "fixed"])