Fix large format

endast · Nov 15, 2023 · 5028329 · 5028329
1 parent c311944
commit 5028329
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 4 deletions.
diff --git a/fake_vcf/vcf_faker.py b/fake_vcf/vcf_faker.py
@@ -37,21 +37,21 @@ def __init__(
                 '##INFO=<ID=AF,Number=A,Type=Float,Description="Estimated allele frequency in the range (0,1)">',
                 '##INFO=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth; some reads may have been filtered">',
                 '##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">',
+                "",
             ]
         )  # VCF file format header
 
         if self.large_format:
-            "\n".join(
+            self.header += "\n".join(
                 [
                     '##FORMAT=<ID=AD,Number=R,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">',
                     '##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Approximate read depth (reads with MQ=255 or with bad mates are filtered)">',
                     '##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">',
                     '##FORMAT=<ID=PL,Number=G,Type=Integer,Description="Phred-scaled genotype Likelihoods">',
+                    "",
                 ]
             )
 
-        self.header += "\n"
-
         if num_samples < 1 or num_rows < 1:
             raise ValueError(f"Nr of samples and rows must be greater or equal to 1")
 
@@ -154,7 +154,10 @@ def _generate_vcf_row(self):
         qual = f"{self.random.randint(10, 100)}"
         filt = self.random.choice(["PASS"])
         info = f"DP=10;AF=0.5;NS={self.num_samples}"
-        fmt = "GT"
+        if self.large_format:
+            fmt = "GT:AD:DP:GQ:PL"
+        else:
+            fmt = "GT"
 
         # Generate random values for each sample by rotating the sample list randomly
         max_rotation = (

diff --git a/tests/test_example/test_vcf_validator.py b/tests/test_example/test_vcf_validator.py
@@ -57,6 +57,7 @@ def run_vcf_validator(vcf_file_path, result_path):
         (["-r", "10", "--no-large-format"],),
         (["-r", "50", "--no-large-format"],),
         (["-r", "100", "--no-large-format"],),
+        (["-r", "10", "--large-format"],),
     ],
 )
 def test_vcf_file_validation(cli_args: list, tmp_path):