tests/test_kn.py

# tests/test_kn.py
import gzip
import json
from pathlib import Path

from fractus_vorax.compiler.kn import compile_kn, load_kn, source_sha256


def _csv(tmp_path):
    p = tmp_path / "cap.csv"
    p.write_text(
        "question,answer\nwhat is the capital of france,paris\nwho wrote hamlet,william shakespeare\n",
        encoding="utf-8",
    )
    return p


def test_compile_produces_kn_layout(tmp_path):
    kn = compile_kn(_csv(tmp_path), tmp_path / "cap.kn")
    assert (kn / "manifest.json").exists()
    assert (kn / "atoms.tsv.gz").exists()
    assert (kn / "signature.bin").exists()
    manifest = json.loads((kn / "manifest.json").read_text(encoding="utf-8"))
    assert manifest["n_atoms"] == 2
    assert manifest["format_version"] == 1
    assert "created" not in manifest  # jamais de timestamp


def test_load_kn_roundtrip(tmp_path):
    src = _csv(tmp_path)
    kn = compile_kn(src, tmp_path / "cap.kn")
    atoms = load_kn(kn)
    assert atoms[0].statement == "what is the capital of france"
    assert atoms[0].context == "paris"
    assert atoms[0].confidence == 1.0


def test_compile_is_bit_identical(tmp_path):
    src = _csv(tmp_path)
    k1 = compile_kn(src, tmp_path / "a.kn")
    k2 = compile_kn(src, tmp_path / "b.kn")
    for name in ("manifest.json", "atoms.tsv.gz", "signature.bin"):
        assert (k1 / name).read_bytes() == (k2 / name).read_bytes(), name


def test_source_sha256_stable(tmp_path):
    src = _csv(tmp_path)
    assert source_sha256(src) == source_sha256(src)
    assert len(source_sha256(src)) == 64


def test_manifest_records_source_hash(tmp_path):
    src = _csv(tmp_path)
    kn = compile_kn(src, tmp_path / "cap.kn")
    manifest = json.loads((kn / "manifest.json").read_text(encoding="utf-8"))
    assert manifest["source_sha256"] == source_sha256(src)