P1: file parsers, sample sheet, discovery, CLI inspect

Readers for IDAT v3, BPM (locus entries v4-v8), CSV manifest, EGT
(data blocks 5-9) and GTC v3-v5 (plus a layout-preserving GTC writer);
sample-sheet validation (IN-001..IN-014), IDAT discovery and pairing
(IN-020..IN-022), message catalogue and exit codes (CLI-014/016),
JSON Lines logging (CLI-007/008), atomic writes (CLI-011), run manifest,
and `simurg inspect`.

Validation (docs/validation/P1.md): GTC, BPM and EGT readers agree
exactly with Illumina BeadArrayFiles on GSA v4 / GDA v1 files; GTCs
round-trip byte-identically; BPM and CSV manifests are consistent.
This commit is contained in:
kemal committed 2026-09-27 16:56:39 +01:00
1 parent 0a421dffc9
commit 5a20e7131c
40 files changed
+4742

No files matched your search

+45
View File
@@ -0,0 +1,45 @@
"""Shared test configuration.
Tests marked ``data`` need files fetched by ``scripts/fetch_data.sh p0``; tests marked ``oracle`` need
reference repositories under ``refs/`` (``scripts/bootstrap_refs.sh``). Both are skipped when absent.
"""
from __future__ import annotations
import sys
from pathlib import Path
import pytest
ROOT = Path(__file__).resolve().parents[1]
DATA = ROOT / "data" / "p0"
REFS = ROOT / "refs"
GSA = DATA / "gsa_v4_pgx"
GSA_BPM = GSA / "GSA-PGx-48v4-0_20079540_E2_bpm" / "GSA-PGx-48v4-0_20079540_E2.bpm"
GSA_CSV = GSA / "GSA-PGx-48v4-0_20079540_E2_csv" / "GSA-PGx-48v4-0_20079540_E2.csv"
GSA_EGT = GSA / "GSA-PGx-48v4-0_20079540_E2_ClusterFile" / "GSA-PGx-48v4-0_20079540_E2_ClusterFile.egt"
GSA_IDATS = GSA / "idats_Demo_36" / "idats_Demo_36"
GDA_EGT = DATA / "gda_v1" / "infinium-global-diversity-array-8-v1-0-D1-cluster-file" / "GDA-8v1-0_D1_ClusterFile.egt"
GDA_BPM = DATA / "gda_v1" / "infinium-global-diversity-array-8-v1-0-D1-manifest-file-bpm" / "GDA-8v1-0_D1.bpm"
GDA_SHEET = DATA / "gda_v1" / "infinium-global-diversity-array-8-v1-0_D1_SampleSheet_Demo_36.csv"
BIOC_IDATS = DATA / "bioc" / "IlluminaDataTestFiles_1.50.0" / "IlluminaDataTestFiles" / "inst" / "extdata" / "idat"
ORACLE_GTCS = DATA / "oracle" / "gsa_gtc_gtc2vcf"
def need(*paths: Path) -> None:
missing = [p for p in paths if not p.exists()]
if missing:
pytest.skip(f"missing test data: {missing[0]} (run scripts/fetch_data.sh p0)")
@pytest.fixture(scope="session")
def beadarrayfiles(): # type: ignore[no-untyped-def]
"""Illumina BeadArrayFiles (BSD-2) as an oracle."""
path = REFS / "BeadArrayFiles"
if not (path / "module").is_dir():
pytest.skip("refs/BeadArrayFiles not present (run scripts/bootstrap_refs.sh)")
sys.path.insert(0, str(path))
import module # type: ignore[import-not-found]
return module