from pathlib import Path

import pytest

import scripts.decisions_lib as dl

FIX = Path(__file__).parent / "fixtures" / "sample_decisions.md"


def test_parses_migrated_record():
    recs = dl.parse_file(FIX)
    migrated = [r for r in recs if r.key == "ci.runner-placement"]
    assert len(migrated) == 1
    r = migrated[0]
    assert r.status == "active"
    assert r.since == "2026-07-17"
    assert r.supersedes == "none"
    assert r.superseded_by == "none"
    assert r.rule == "Every CI services container gets an explicit cap."
    assert r.signals is not None
    assert "issues: #390 #406" in r.signals
    assert r.mechanics is not None
    assert r.mechanics.startswith("docs/ci-cd.md")


def test_legacy_record_is_unmigrated():
    recs = dl.parse_file(FIX)
    legacy = [r for r in recs if r.heading.endswith("(#231)")]
    assert len(legacy) == 1
    assert legacy[0].key is None
    assert legacy[0].status == "legacy-unmigrated"


def test_index_section_parses_as_heading():
    recs = dl.parse_file(FIX)
    assert any(r.heading == "Index" for r in recs)


def test_parses_optional_stale_after_and_sources():
    recs = dl.parse_file(FIX)
    r = next(r for r in recs if r.key == "ci.peak-anon-measurement")
    assert r.stale_after == "2027-01-15"
    assert r.sources is not None
    assert "gitea run 4471" in r.sources


def test_optional_fields_default_to_none_when_absent():
    recs = dl.parse_file(FIX)
    r = next(r for r in recs if r.key == "ci.runner-placement")
    assert r.stale_after is None
    assert r.sources is None


def test_empty_stale_after_parses_as_empty_string_not_none():
    """Absent vs present-but-empty must stay distinguishable for the validator."""
    text = (
        "## H\n"
        "`key: a.b` · `status: active` · `since: 2026-01-01` · `stale-after:` "
        "· `supersedes: none` · `superseded-by: none`\n"
        "**Rule:** r\n"
    )
    r = dl.parse_text(text, Path("fake.md"))[0]
    assert r.stale_after == ""


def test_frontmatter_reader_matches_pyyaml_on_every_real_record():
    """The dependency-free reader must agree with PyYAML on the whole real corpus.

    The read path cannot import PyYAML — it runs in CI's `decisions lifecycle` job, the Husky
    pre-commit hook, and on every contributor's machine, none of which install it. (Requiring it
    made the validator crash with ModuleNotFoundError once the corpus was migrated.) A hand parser
    is only safe if it provably matches the library that WROTE the files, so this compares the two
    across every record rather than on a sample.
    """
    yaml = pytest.importorskip("yaml")

    files = [p for p in dl.RECORDS_DIR.rglob("*.md")] + [p for p in dl.ARCHIVE_DIR.rglob("*.md")]
    files = [f for f in files if dl.has_frontmatter(f.read_text(encoding="utf-8"))]
    assert len(files) > 100, f"only {len(files)} frontmatter files found — test would be near-vacuous"

    diffs = []
    for f in files:
        lines = f.read_text(encoding="utf-8").splitlines()
        end = next(i for i, ln in enumerate(lines[1:], start=1) if ln.rstrip() == "---")
        block = "\n".join(lines[1:end])
        mine = dl._read_frontmatter(block)
        theirs = yaml.safe_load(block) or {}
        theirs = {k: ("" if v is None else str(v)) for k, v in theirs.items()}
        if mine != theirs:
            for k in set(mine or {}) | set(theirs):
                if (mine or {}).get(k) != theirs.get(k):
                    diffs.append(f"{f.name}:{k}\n  mine  ={(mine or {}).get(k)!r}\n  pyyaml={theirs.get(k)!r}")
    assert not diffs, f"{len(diffs)} field(s) differ from PyYAML:\n" + "\n".join(diffs[:5])