Handle case where VCF filter is not defined in the header

Author: tomwhite

sgkit/io/vcf/vcf_reader.py

@@ -456,9 +456,11 @@ def vcf_to_zarr_sequential(
                 variant_quality[i] = (
                     variant.QUAL if variant.QUAL is not None else FLOAT32_MISSING
                 )
-                for f in variant.FILTERS:
-                    variant_filter[i][filters.index(f)] = True
-
+                try:
+                    for f in variant.FILTERS:
+                        variant_filter[i][filters.index(f)] = True
+                except ValueError:
+                    raise ValueError(f"Filter '{f}' is not defined in the header.")
                 for field_handler in field_handlers:
                     field_handler.add_variant(i, variant)
 

sgkit/tests/io/vcf/data/no_filter_defined.vcf

@@ -0,0 +1,14 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##fileDate=20201009
+##source=.
+##reference=./simple.fasta
+##contig=<ID=CHR1,length=60>
+##contig=<ID=CHR2,length=60>
+##contig=<ID=CHR3,length=60>
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of samples with data">
+##INFO=<ID=AC,Number=A,Type=Integer,Description="Total number of alternate alleles in called genotypes">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	SAMPLE1	SAMPLE2	SAMPLE3
+CHR1	2	.	A	T	60	PASS	NS=3;AC=3	GT	0/0	0/0	0/0
+CHR1	7	.	A	C	60	FAIL	NS=3;AC=4	GT	0/0	0/1	0/1

sgkit/tests/io/vcf/test_vcf_reader.py

@@ -727,6 +727,17 @@ def test_vcf_to_zarr__contig_not_defined_in_header(shared_datadir, tmp_path):
         vcf_to_zarr(path, output)
 
 
+def test_vcf_to_zarr__filter_not_defined_in_header(shared_datadir, tmp_path):
+    path = path_for_test(shared_datadir, "no_filter_defined.vcf")
+    output = tmp_path.joinpath("vcf.zarr").as_posix()
+
+    with pytest.raises(
+        ValueError,
+        match=r"Filter 'FAIL' is not defined in the header.",
+    ):
+        vcf_to_zarr(path, output)
+
+
 def test_vcf_to_zarr__large_number_of_contigs(shared_datadir, tmp_path):
     path = path_for_test(shared_datadir, "Homo_sapiens_assembly38.headerOnly.vcf.gz")
     output = tmp_path.joinpath("vcf.zarr").as_posix()