"""The failure-artifact collector (US07-04).

CI must be able to explain a randomized failure after the temporary library is
gone, which means the seed, the database, the journals, the logs, and a complete
filesystem manifest have to leave the temporary directory before pytest cleans it.
"""

from __future__ import annotations

import hashlib
import json

from tests._artifacts import collect, manifest


def _library(root):
    (root / "data").mkdir(parents=True)
    (root / "data" / "photo_pipeline.db").write_bytes(b"database bytes")
    (root / "data" / "photo_pipeline.db-wal").write_bytes(b"write ahead log")
    (root / "data" / "uploads").mkdir()
    (root / "data" / "uploads" / "batch.log").write_text("INFO uploaded a.jpg\n")
    (root / "lib").mkdir()
    (root / "lib" / "a.jpg").write_bytes(b"pixels")
    return root


def test_the_manifest_covers_every_file_with_its_hash(tmp_path):
    root = _library(tmp_path / "run")
    entries = {entry["path"]: entry for entry in manifest(root)}

    assert set(entries) == {
        "data/photo_pipeline.db",
        "data/photo_pipeline.db-wal",
        "data/uploads/batch.log",
        "lib/a.jpg",
    }
    assert entries["lib/a.jpg"]["sha256"] == hashlib.sha256(b"pixels").hexdigest()
    assert entries["lib/a.jpg"]["bytes"] == 6


def test_collect_keeps_the_database_journals_logs_and_seed(tmp_path, monkeypatch):
    root = _library(tmp_path / "run")
    monkeypatch.setenv("PHOTO_PIPELINE_TEST_ARTIFACTS", str(tmp_path / "artifacts"))

    destination = collect(root, "tests/x.py::test_races[run1]", properties={"race_seed": 1234})

    seeds = json.loads((destination / "seeds.json").read_text())
    assert seeds["properties"]["race_seed"] == 1234
    assert seeds["test"].endswith("test_races[run1]")

    kept = {str(p.relative_to(destination / "files")) for p in (destination / "files").rglob("*") if p.is_file()}
    assert kept == {
        "data/photo_pipeline.db",
        "data/photo_pipeline.db-wal",
        "data/uploads/batch.log",
    }, "databases, write-ahead logs, and logs are the diagnosable evidence"
    # The photo itself is never copied out of the library — but it is in the
    # manifest, so a file that went missing is still provable.
    assert any(entry["path"] == "lib/a.jpg" for entry in json.loads((destination / "manifest.json").read_text()))


def test_collecting_twice_for_one_test_is_safe(tmp_path, monkeypatch):
    root = _library(tmp_path / "run")
    monkeypatch.setenv("PHOTO_PIPELINE_TEST_ARTIFACTS", str(tmp_path / "artifacts"))

    first = collect(root, "tests/x.py::test_a")
    second = collect(root, "tests/x.py::test_a")

    assert first == second and (second / "manifest.json").exists()