"""Module-level constants + shared job state for the compliance-check
route.

`_compliance_check_jobs` is the SINGLE source of truth for in-flight
job progress. Other modules MUST import the same object — never
re-declare it — otherwise progress updates land in a detached dict.
"""

from __future__ import annotations

# Internal hostname of the consent-tester container.
CONSENT_TESTER_URL = "http://bp-compliance-consent-tester:8094"

# In-memory job registry. Keyed by check_id. Values:
#   {"status": "running"|"completed"|"failed"|"skipped_tdm",
#    "progress": str, "progress_pct": int, "result": dict, ...}
# Read/written by:
#   - agent_compliance_check_routes (start/status/_run/_update)
#   - saving_scan_routes (start)
#   - agent_migration_routes (status mirror)
_compliance_check_jobs: dict[str, dict] = {}


# Canonical doc types in the same order the frontend
# ComplianceCheckTab renders them. The route pads `results` to always
# include an entry for each — missing rows are flagged as 'Nicht
# eingereicht' or 'Auf der Website nicht gefunden'.
#
# DSB-Kontakt is NOT canonical: per GDPR practice the DSB is named
# inside the DSI/datenschutz document (email or contact block), not as
# a separate page. We check 'DSB benannt' as a sub-check of the DSE.
_ALL_DOC_TYPES = [
    "dse", "impressum", "social_media", "cookie",
    "agb", "nutzungsbedingungen", "widerruf",
]


# Human-readable labels per doc_type. Used in the report + emails.
_DOC_TYPE_LABELS = {
    "dse": "Datenschutzerklaerung",
    "datenschutz": "Datenschutzerklaerung",
    "privacy": "Datenschutzerklaerung",
    "impressum": "Impressum",
    "agb": "AGB",
    "widerruf": "Widerrufsbelehrung",
    "cookie": "Cookie-Richtlinie",
    "avv": "Auftragsverarbeitung",
    "loeschkonzept": "Loeschkonzept",
    "dsfa": "Datenschutz-Folgenabschaetzung",
    "social_media": "Social Media Datenschutz",
    "nutzungsbedingungen": "Nutzungsbedingungen",
    "dsb": "DSB-Kontakt",
    # P74: Legal-Notice / Rechtliche Hinweise (IP, Forward-Looking, Risiko)
    "legal_notice": "Rechtliche Hinweise",
    # P96: Digital Services Act-Pflichtangaben (Art. 12+17 DSA)
    "dsa": "DSA-Pflichtangaben",
    # P97: Lizenzhinweise Dritter (OSS-Compliance)
    "lizenzhinweise": "Lizenzhinweise Dritter",
}


# Title/URL keywords → canonical doc_type. Order matters: most-specific first.
_DISCOVERY_RULES: list[tuple[str, tuple[str, ...]]] = [
    ("cookie",            ("cookie", "kuche", "biscuit", "cookies-")),
    ("widerruf",          ("widerruf", "rueckgabe", "rückgabe", "cancellation",
                           "right-of-withdrawal", "ruecktritts", "rücktritts")),
    ("social_media",      ("social-media", "soziale-medien", "social_media",
                           "social-media-policy")),
    # P23: 'terms-and-conditions' kann Allgemeine Geschaeftsbedingungen ODER
    # Nutzungsbedingungen meinen. Discovery-Funktion klassifiziert spaeter
    # praeziser per Titel + Inhalt. Hier nur Url-Hint:
    ("agb",               ("/agb", "geschaeftsbedingungen", "geschäftsbedingungen",
                           "general-terms")),
    ("nutzungsbedingungen", ("nutzungsbedingung", "nutzungsbedingungen",
                              "terms-of-use", "terms-and-conditions",
                              "nutzungsordnung", "terms-of-service",
                              "allgemeine-nutzungsbedingungen")),
    ("dsb",               ("datenschutzbeauftragt", "data-protection-officer",
                           "dpo-contact", "/dsb")),
    ("impressum",         ("impressum", "imprint", "legal-notice", "site-notice",
                           "anbieterkennzeichnung", "legal-disclaimer-pool")),
    ("dse",               ("data-privacy", "datenschutz", "data-protection",
                           "privacy-policy", "privacy-notice", "dsgvo",
                           "data_privacy", "datenschutzinformation")),
]


# Compound TLDs that count as 2 labels when extracting the second-level
# domain (e.g. shop.example.co.uk → 'example', not 'co').
_COMPOUND_TLDS = {
    "co.uk", "co.jp", "co.nz", "co.kr", "co.za", "co.in",
    "com.au", "com.br", "com.mx", "com.tr", "com.sg",
}