"""Tests for the Regulatory Completeness Engine — auditable coverage, not confidence.

Acceptance: separate identified from assessed regulations; justify every gap (corpus gap ->
future_corpus, applicability uncertain -> query_required with a deciding question); report counts
(never a single percentage); emit an honest audit statement. The product shows what it does NOT
know and why.
"""

from __future__ import annotations

from compliance.completeness import CompletenessReport, CorpusStatus, assess_completeness

IDENTIFIED = ["CRA", "MaschinenVO", "EMV", "Environmental", "DataAct"]
CORPUS = {"CRA": "validated", "MaschinenVO": "validated", "EMV": "validated",
          "Environmental": "unsupported", "DataAct": "validated"}
UNCERTAIN = [{"regulation": "DataAct", "deciding_question": "generates_usage_data", "reason": "generates_usage_data unbekannt"}]


def _report():
    return assess_completeness(IDENTIFIED, CORPUS, uncertain=UNCERTAIN,
                               assumptions=[{"key": "funkmodul", "value": "nein"}], assessed_obligations=128)


def test_assessed_excludes_uncertain_even_if_corpus_validated():
    r = _report()
    # DataAct has a validated corpus but uncertain applicability -> NOT assessed
    assert r.assessed_regulations == ["CRA", "EMV", "MaschinenVO"]
    assert "DataAct" in r.open_regulations and "Environmental" in r.open_regulations


def test_corpus_gap_vs_applicability_exclusion():
    r = _report()
    by = {e.subject: e for e in r.exclusions}
    assert by["DataAct"].resolution == "query_required" and by["DataAct"].deciding_question == "generates_usage_data"
    assert by["Environmental"].resolution == "future_corpus"


def test_open_corpora_is_unsupported_only():
    r = _report()
    # DataAct corpus is validated (only applicability is open) -> NOT an open corpus
    assert r.open_corpora == ["Environmental"]


def test_justification_present_when_every_gap_has_a_reason():
    r = _report()
    assert r.justification_present is True
    open_subjects = {e.subject for e in r.exclusions}
    assert set(r.open_regulations) <= open_subjects


def test_counts_summary_has_no_percentage():
    r = _report()
    assert "%" not in r.completeness_summary and "%" not in r.audit_statement
    assert "Identifiziert 5" in r.completeness_summary and "bewertet 3" in r.completeness_summary


def test_audit_statement_is_honest():
    r = _report()
    assert "3 von 5" in r.audit_statement and "bewusst nicht bewertet" in r.audit_statement


def test_draft_corpus_is_in_review_exclusion():
    r = assess_completeness(["CRA", "IEC62443"], {"CRA": "validated", "IEC62443": "draft"})
    by = {e.subject: e for e in r.exclusions}
    assert by["IEC62443"].resolution == "in_review"
    assert "IEC62443" in r.open_regulations and "IEC62443" not in r.open_corpora   # draft != missing corpus


def test_all_assessed_no_open():
    r = assess_completeness(["CRA", "MaschinenVO"], {"CRA": "validated", "MaschinenVO": "validated"})
    assert r.open_regulations == [] and r.exclusions == []
    assert r.justification_present is True
    assert "alle 2" in r.audit_statement


def test_coverage_status_mapped():
    r = _report()
    cov = {c.regulation: c.status for c in r.coverage}
    assert cov["CRA"] == CorpusStatus.VALIDATED and cov["Environmental"] == CorpusStatus.UNSUPPORTED


def test_assumptions_and_obligations_carried():
    r = _report()
    assert r.assessed_obligations == 128
    assert [a.key for a in r.assumptions] == ["funkmodul"]


def test_unknown_regulation_defaults_to_open_corpus():
    r = assess_completeness(["CRA", "REACH"], {"CRA": "validated"})   # REACH not in registry -> unknown
    assert "REACH" in r.open_corpora and r.assessed_regulations == ["CRA"]


def test_deterministic_and_type():
    r1 = _report()
    r2 = _report()
    assert r1.model_dump() == r2.model_dump()
    assert isinstance(r1, CompletenessReport)