breakpilot-compliance/backend-compliance/tests/test_migration_mappers.py

"""
Unit tests for vendor → CookieBannerConfig and vendor → Document pre-fill
mappers (M1 + M2 of the customer-banner migration feature).
"""

from __future__ import annotations

import pytest

from compliance.services.migration_to_banner import (
    build_banner_config, map_category,
)
from compliance.services.migration_to_document import build_document_prefills


@pytest.fixture()
def sample_vendors() -> list[dict]:
    return [
        {
            "name": "BMW AG",
            "category": "necessary",
            "recipient_type": "INTERNAL",
            "purpose": "Sicherstellung der Grundfunktionen",
            "cookies": [{"name": "JSESSIONID", "expiry": "Session"}],
        },
        {
            "name": "Google Analytics",
            "category": "statistics",
            "recipient_type": "PROCESSOR",
            "purpose": "Reichweitenmessung",
            "country": "US",
            "opt_out_url": "https://tools.google.com/dlpage/gaoptout",
            "opt_out_ok": True,
            "privacy_policy_url": "https://policies.google.com/privacy",
            "cookies": [
                {"name": "_ga", "expiry": "2 Jahre", "is_third_party": True},
                {"name": "_gid", "expiry": "1 Tag", "is_third_party": True},
            ],
        },
        {
            "name": "YouTube",
            "category": "marketing",
            "recipient_type": "PROCESSOR",
            "purpose": "Eingebettete Videos",
            "cookies": [],
        },
        {
            "name": "Broken Pixel",
            "category": "marketing",
            "recipient_type": "PROCESSOR",
            "purpose": "Werbung",
            "opt_out_url": "https://example.com/optout",
            "opt_out_ok": False,
            "opt_out_status": 404,
            "cookies": [{"name": "_pix", "expiry": ""}],
        },
    ]


def test_map_category_youtube_routes_to_external_media():
    assert map_category("marketing", "YouTube Player") == "EXTERNAL_MEDIA"


def test_map_category_unknown_falls_back_to_personalization():
    assert map_category("weird-cat", "Some Vendor") == "PERSONALIZATION"


def test_map_category_necessary_is_essential():
    assert map_category("necessary", "JSESSIONID") == "ESSENTIAL"


def test_build_banner_config_buckets_categories(sample_vendors):
    out = build_banner_config(sample_vendors, site_name="bmw.de")
    cats = {c["id"]: c for c in out["config"]["categories"]}
    assert "ESSENTIAL" in cats
    assert "PERFORMANCE" in cats
    assert any(c["name"] == "_ga" for c in cats["PERFORMANCE"]["cookies"])
    # YouTube vendor had no cookies → it should not pollute EXTERNAL_MEDIA
    # but should produce a WARNING flag for the missing list
    assert any(f["vendor"] == "YouTube" and f["issue"] == "no_cookies_listed"
               for f in out["flags"])


def test_build_banner_config_flags_broken_opt_out(sample_vendors):
    out = build_banner_config(sample_vendors, site_name="bmw.de")
    errors = [f for f in out["flags"] if f["level"] == "ERROR"]
    assert any(f["issue"] == "broken_opt_out" and f["vendor"] == "Broken Pixel"
               for f in errors)


def test_build_banner_config_summary_counts(sample_vendors):
    out = build_banner_config(sample_vendors, site_name="bmw.de")
    s = out["summary"]
    assert s["vendors_total"] == 4
    assert s["vendors_with_no_cookies"] == 1
    assert s["cookies_total"] == 4  # JSESSIONID + _ga + _gid + _pix


def test_build_document_prefills_emits_all_three_templates(sample_vendors):
    out = build_document_prefills(
        sample_vendors,
        extracted_profile={
            "company_profile": {
                "companyName": "BMW AG",
                "headquartersStreet": "Petuelring 130",
                "headquartersZip": "80809",
                "headquartersCity": "Muenchen",
                "dpoEmail": "datenschutz@bmw.de",
            },
        },
        site_name="bmw.de",
    )
    assert set(out.keys()) == {"cookie_policy", "vvt_register", "privacy_policy"}
    cp = out["cookie_policy"]
    assert cp["templateType"] == "cookie_policy"
    assert "BMW AG" in cp["initialContent"]
    assert "Google Analytics" in cp["initialContent"]
    assert "Petuelring 130" in cp["initialContent"]


def test_vvt_register_marks_third_country_for_us_processor(sample_vendors):
    out = build_document_prefills(sample_vendors, site_name="bmw.de")
    acts = out["vvt_register"]["activities"]
    ga = next(a for a in acts if a["name"] == "Google Analytics")
    rcat = ga["recipientCategories"][0]
    assert rcat["type"] == "PROCESSOR"
    assert rcat["country"] == "US"
    assert rcat["isThirdCountry"] is True


def test_privacy_policy_section_groups_by_recipient_type(sample_vendors):
    out = build_document_prefills(sample_vendors, site_name="bmw.de")
    body = out["privacy_policy"]["initialContent"]
    assert "Eigene Verarbeitung" in body
    assert "Auftragsverarbeiter" in body
    # BMW AG (INTERNAL) must appear under Eigene, not under Auftragsverarbeiter
    internal_block = body.split("### Auftragsverarbeiter")[0]
    assert "BMW AG" in internal_block