from pathlib import Path

import pytest

from repo_manager.observe import RecordIdentityCollisionError, observe_repository
from repo_manager.record_identity import classify_record_id, scan_record_identities
from repo_manager.standards import check_repository


def _write_mason_workplan(repo: Path, second_uuid: str) -> None:
    path = repo / "workplans" / "MASON-0001-statehub-bootstrap.md"
    path.parent.mkdir(parents=True)
    path.write_text(
        f"""---
id: MASON-0001
type: workplan
title: Bootstrap
status: finished
state_hub_workstream_id: "11111111-1111-4111-8111-111111111111"
---

## First occurrence

```task
id: MASON-0001-T01
status: done
priority: high
state_hub_task_id: "ede1aa62-fc42-494a-9984-3190a52481af"
```

## Second occurrence

```task
id: MASON-0001-T01
status: done
priority: high
state_hub_task_id: "{second_uuid}"
```
""",
        encoding="utf-8",
    )


def test_grandfathered_mason_identity_is_loaded_from_canon_registry() -> None:
    assert classify_record_id("workplan", "MASON-0001") == "grandfathered"
    assert classify_record_id("task", "MASON-0001-T01") == "grandfathered"


def test_current_canon_accepts_repository_and_ad_hoc_workplan_forms() -> None:
    assert classify_record_id("workplan", "RAPP-OPENBAO-WP-0002") == "canonical"
    assert classify_record_id("task", "RAPP-OPENBAO-WP-0002-T01") == "canonical"
    assert classify_record_id("workplan", "ACTIVITY-WP-ADHOC-2026-08-23") == "canonical"
    assert classify_record_id("task", "ACTIVITY-WP-ADHOC-2026-08-23-T01") == "canonical"
    assert classify_record_id("workplan", "ADHOC-2026-08-23") == "grandfathered"
    assert classify_record_id("task", "ADHOC-2026-08-23-T01") == "grandfathered"
    assert classify_record_id("workplan", "RAPP--OPENBAO-WP-0002") is None


def test_same_id_and_uuid_indexes_once_with_cleanup_diagnostic(tmp_path: Path) -> None:
    _write_mason_workplan(tmp_path, "ede1aa62-fc42-494a-9984-3190a52481af")

    report = scan_record_identities(tmp_path)
    assert report["identity_collisions"] == []
    assert report["duplicate_source_occurrences"][0]["sources"] == [
        "workplans/MASON-0001-statehub-bootstrap.md#task-block-1",
        "workplans/MASON-0001-statehub-bootstrap.md#task-block-2",
    ]

    snapshot, index = observe_repository(tmp_path, slug="ops-mason")
    tasks = [record for record in index.work_records if record.kind == "task"]
    assert snapshot["index"]["task_count"] == 1
    assert len(tasks) == 1
    assert (
        tasks[0].extra["source_occurrences"] == report["duplicate_source_occurrences"][0]["sources"]
    )
    assert index.events[0]["type"] == "repo.work_record.duplicate_source_occurrence"

    conformance = check_repository(tmp_path, slug="ops-mason")
    codes = [finding.code for finding in conformance.findings]
    assert "work-record-duplicate-source-occurrence" in codes
    assert not any(
        finding.code == "work-record-id-invalid" and finding.path.startswith("workplans/")
        for finding in conformance.findings
    )


def test_same_id_with_different_uuids_fails_closed(tmp_path: Path) -> None:
    _write_mason_workplan(tmp_path, "22222222-2222-4222-8222-222222222222")

    report = scan_record_identities(tmp_path)
    assert report["duplicate_source_occurrences"] == []
    assert report["identity_collisions"][0]["id"] == "MASON-0001-T01"
    with pytest.raises(RecordIdentityCollisionError):
        observe_repository(tmp_path, slug="ops-mason")

    conformance = check_repository(tmp_path, slug="ops-mason")
    assert any(finding.code == "work-record-identity-collision" for finding in conformance.findings)