"""Regression guards for canonical documentation and instruction contracts."""

from __future__ import annotations

import re
from pathlib import Path

from transcription.config import Settings

PROJECT_ROOT = Path(__file__).resolve().parents[1]


ACTIVE_CONTRACT_FILES = (
    ".github/instructions/services.instructions.md",
    ".github/instructions/ui.instructions.md",
    ".github/instructions/error-handling.instructions.md",
    ".github/skills/python-code-reviewer/skill.md",
    ".github/skills/evidence-provenance-auditor/skill.md",
    "docs/index.md",
    "docs/architecture.md",
    "docs/requirements.md",
    "docs/schema.md",
    "docs/error_handling.md",
    "docs/ui/README.md",
)


LEGACY_REFERENCE_MARKERS = (
    "docs-v4x-archive",
    "docs/ver4/history.md",
    "docs/ver4.0",
    "docs/ver4.1",
    "docs/ver4.2",
    "docs/ver4.3",
    "docs/ver4.4",
    "docs/ver4.5",
    "docs/ver4.6",
    "docs/ver4.7",
)


def _read(relative_path: str) -> str:
    return (PROJECT_ROOT / relative_path).read_text(encoding="utf-8")


def test_active_contract_files_are_present():
    """Guard the guard: ensure all expected authority files are scanned."""
    missing = [path for path in ACTIVE_CONTRACT_FILES if not (PROJECT_ROOT / path).exists()]
    assert missing == []


def test_no_legacy_authority_references_in_active_contract_files():
    """Active contracts must not route authority through removed revision trees."""
    violations: dict[str, list[str]] = {}
    for relative_path in ACTIVE_CONTRACT_FILES:
        text = _read(relative_path)
        found = [marker for marker in LEGACY_REFERENCE_MARKERS if marker in text]
        if found:
            violations[relative_path] = found
    assert violations == {}


def test_canonical_authority_references_are_present():
    """Critical instruction and skill files must keep canonical references explicit."""
    required_fragments = {
        ".github/instructions/services.instructions.md": (
            "docs/",
            "./error-handling.instructions.md",
            "src/transcription/db/models.py",
            "docs/schema.md",
            "append-only",
        ),
        ".github/instructions/ui.instructions.md": (
            "docs/",
            "./error-handling.instructions.md",
            "src/transcription/db/models.py",
            "docs/schema.md",
        ),
        ".github/instructions/error-handling.instructions.md": (
            "docs/error_handling.md",
            "docs/requirements.md",
        ),
        ".github/skills/python-code-reviewer/skill.md": (
            "docs/*",
            "docs/schema.md",
            ".github/instructions/error-handling.instructions.md",
        ),
        ".github/skills/evidence-provenance-auditor/skill.md": (
            "docs/schema.md",
            "docs/requirements.md",
            "docs/error_handling.md",
        ),
    }

    missing: dict[str, list[str]] = {}
    for relative_path, fragments in required_fragments.items():
        text = _read(relative_path)
        absent = [fragment for fragment in fragments if fragment not in text]
        if absent:
            missing[relative_path] = absent
    assert missing == {}


def _declared_env_example_keys(*, include_commented: bool) -> set[str]:
    text = _read(".env.example")
    pattern = r"^\s*#?\s*([A-Z0-9_]+)\s*=" if include_commented else r"^\s*([A-Z0-9_]+)\s*="
    return {match.group(1) for match in re.finditer(pattern, text, flags=re.MULTILINE)}


def _active_env_example_values() -> dict[str, str]:
    text = _read(".env.example")
    return {key: value.strip() for key, value in re.findall(r"^\s*([A-Z0-9_]+)\s*=\s*(.*)$", text, flags=re.MULTILINE)}


def _normalize_env_path_value(value: str | None) -> str | None:
    if value is None:
        return None
    normalized = value.strip().replace("\\", "/")
    while normalized.startswith("./"):
        normalized = normalized[2:]
    return normalized


def test_env_example_keys_match_runtime_settings_contract():
    """Guard against .env.example drift from Settings keys."""
    declared = _declared_env_example_keys(include_commented=True)
    settings_keys = {field.upper() for field in Settings.model_fields if field != "database"}
    database_keys = {
        "DATABASE__DRIVER",
        "DATABASE__PATH",
        "DATABASE__HOST",
        "DATABASE__PORT",
        "DATABASE__DATABASE",
        "DATABASE__USER",
        "DATABASE__PASSWORD",
    }
    allowed = settings_keys | database_keys

    missing = sorted(allowed - declared)
    unknown = sorted(declared - allowed)
    assert missing == []
    assert unknown == []


def test_env_example_default_values_match_settings_defaults():
    """Uncommented .env.example entries should mirror in-code defaults."""
    defaults = Settings(_env_file=None, openrouter_api_key="placeholder-key")
    expected = {
        "HOST": defaults.host,
        "PORT": str(defaults.port),
        "LOG_LEVEL": defaults.log_level,
        "RELOAD": str(defaults.reload).lower(),
        "LOG_DIR": str(defaults.log_dir),
        "LOG_FILE_NAME": defaults.log_file_name,
        "LOG_FILE_MAX_BYTES": str(defaults.log_file_max_bytes),
        "LOG_FILE_BACKUP_COUNT": str(defaults.log_file_backup_count),
        "PROVIDER": defaults.provider.value,
        "PROVIDER_MODEL": defaults.provider_model or "",
        "DEFAULT_PROMPT_NAME": defaults.default_prompt_name,
        "ENVIRONMENT": defaults.environment,
        "DATABASE__DRIVER": defaults.database.driver,
        "DATABASE__PATH": getattr(defaults.database, "path", ""),
        "BOOTSTRAP_SCHEMA_ON_STARTUP": str(defaults.bootstrap_schema_on_startup).lower(),
        "SQLITE_CHECK_SAME_THREAD": str(defaults.sqlite_check_same_thread).lower(),
        "UPLOAD_DIR": str(defaults.upload_dir),
        "PROMPT_DIR": str(defaults.prompt_dir),
        "DATABASE_BACKUP_DIR": str(defaults.database_backup_dir),
        "WORKER_MAX_RETRIES": str(defaults.worker_max_retries),
        "WORKER_PROVIDER_TIMEOUT_SECONDS": str(defaults.worker_provider_timeout_seconds),
        "WORKER_STALE_JOB_SECONDS": str(defaults.worker_stale_job_seconds),
        "WORKER_RETRY_BACKOFF_SECONDS": str(defaults.worker_retry_backoff_seconds),
        "WORKER_MIN_TRANSCRIPTION_CHARS": str(defaults.worker_min_transcription_chars),
        "WORKER_MIN_TRANSCRIPTION_LINES": str(defaults.worker_min_transcription_lines),
        "WORKER_FAIL_ON_FINISH_REASON_LENGTH": str(defaults.worker_fail_on_finish_reason_length).lower(),
    }
    active = _active_env_example_values()
    path_like_keys = {"LOG_DIR", "UPLOAD_DIR", "PROMPT_DIR", "DATABASE_BACKUP_DIR"}
    mismatches = {
        key: {
            "expected": _normalize_env_path_value(expected_value) if key in path_like_keys else expected_value,
            "actual": _normalize_env_path_value(active.get(key)) if key in path_like_keys else active.get(key),
        }
        for key, expected_value in expected.items()
        if (
            (_normalize_env_path_value(active.get(key)) if key in path_like_keys else active.get(key))
            != (_normalize_env_path_value(expected_value) if key in path_like_keys else expected_value)
        )
    }
    assert mismatches == {}