From e5ae887bd5a5e0ec8d3f0a6cb72387a1cfce9969 Mon Sep 17 00:00:00 2001
From: Tom White <tom.e.white@gmail.com>
Date: Fri, 27 Sep 2024 13:16:29 +0100
Subject: [PATCH 1/2] Get INFO/FORMAT description from attrs if present

---
 vcztools/vcf_writer.py | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/vcztools/vcf_writer.py b/vcztools/vcf_writer.py
index c7db961..53dae3b 100644
--- a/vcztools/vcf_writer.py
+++ b/vcztools/vcf_writer.py
@@ -489,10 +489,9 @@ def _generate_header(ds, original_header, sample_ids, *, no_version: bool = Fals
         category = "INFO"
         vcf_number = _array_to_vcf_number(category, key, arr)
         vcf_type = _array_to_vcf_type(arr)
-        if "comment" in arr.attrs:
-            vcf_description = arr.attrs["comment"]
-        else:
-            vcf_description = RESERVED_INFO_KEY_DESCRIPTIONS.get(key, "")
+        vcf_description = arr.attrs.get(
+            "description", RESERVED_INFO_KEY_DESCRIPTIONS.get(key, "")
+        )
         print(
             f'##INFO=<ID={key},Number={vcf_number},Type={vcf_type},Description="{vcf_description}">',
             file=output,
@@ -514,10 +513,9 @@ def _generate_header(ds, original_header, sample_ids, *, no_version: bool = Fals
             category = "FORMAT"
             vcf_number = _array_to_vcf_number(category, key, arr)
             vcf_type = _array_to_vcf_type(arr)
-            if "comment" in arr.attrs:
-                vcf_description = arr.attrs["comment"]
-            else:
-                vcf_description = RESERVED_FORMAT_KEY_DESCRIPTIONS.get(key, "")
+            vcf_description = arr.attrs.get(
+                "description", RESERVED_FORMAT_KEY_DESCRIPTIONS.get(key, "")
+            )
             print(
                 f'##FORMAT=<ID={key},Number={vcf_number},Type={vcf_type},Description="{vcf_description}">',
                 file=output,

From d590ebdd11a8ab8718deb3fcb88bbf71779aaea8 Mon Sep 17 00:00:00 2001
From: Tom White <tom.e.white@gmail.com>
Date: Fri, 27 Sep 2024 13:43:21 +0100
Subject: [PATCH 2/2] Test generated header

---
 tests/test_vcf_writer.py | 44 ++++++++++++++++++++++++++++++++++++++++
 vcztools/vcf_writer.py   |  2 --
 2 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/tests/test_vcf_writer.py b/tests/test_vcf_writer.py
index 5e562ae..7f680f4 100644
--- a/tests/test_vcf_writer.py
+++ b/tests/test_vcf_writer.py
@@ -4,6 +4,8 @@
 
 import numpy as np
 import pytest
+import zarr
+from bio2zarr import vcf2zarr
 from cyvcf2 import VCF
 from numpy.testing import assert_array_equal
 
@@ -269,6 +271,48 @@ def test_write_vcf__header_flags(tmp_path):
     assert_vcfs_close(original, output)
 
 
+def test_write_vcf__generate_header(tmp_path):
+    original = pathlib.Path("tests/data/vcf") / "sample.vcf.gz"
+    # don't use cache here since we mutate the vcz
+    vcz = tmp_path.joinpath("intermediate.vcz")
+    vcf2zarr.convert([original], vcz, worker_processes=0, local_alleles=False)
+
+    # remove vcf_header
+    root = zarr.open(vcz, mode="r+")
+    del root.attrs["vcf_header"]
+
+    output_header = StringIO()
+    write_vcf(vcz, output_header, header_only=True, no_version=True)
+
+    expected_vcf_header = """##fileformat=VCFv4.3
+##source={}
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=AC,Number=2,Type=Integer,Description="Allele count in genotypes, for each ALT allele, in the same order as listed">
+##INFO=<ID=AF,Number=2,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AN,Number=1,Type=Integer,Description="Total number of alleles in called genotypes">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##FILTER=<ID=PASS,Description="">
+##FILTER=<ID=s50,Description="">
+##FILTER=<ID=q10,Description="">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+##contig=<ID=19>
+##contig=<ID=20>
+##contig=<ID=X>
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	NA00001	NA00002	NA00003
+"""  # noqa: E501
+
+    # substitute value of source
+    expected_vcf_header = expected_vcf_header.format(root.attrs["source"])
+
+    assert output_header.getvalue() == expected_vcf_header
+
+
 def test_compute_info_fields():
     gt = np.array([
         [[0, 0], [0, 1], [1, 1]],
diff --git a/vcztools/vcf_writer.py b/vcztools/vcf_writer.py
index 53dae3b..d4682c3 100644
--- a/vcztools/vcf_writer.py
+++ b/vcztools/vcf_writer.py
@@ -445,8 +445,6 @@ def _generate_header(ds, original_header, sample_ids, *, no_version: bool = Fals
         # [1.4.1 File format]
         print("##fileformat=VCFv4.3", file=output)
 
-        print('##FILTER=<ID=PASS,Description="All filters passed">', file=output)
-
         if "source" in ds.attrs:
             print(f'##source={ds.attrs["source"]}', file=output)