"""CC origin notices for a published source.

The duties follow the license named on the source. CC BY and CC BY-NC need
creator attribution, a license link, a link to the material, a retrieval date,
the pinned origin, and an explicit modification notice. CC0 does not require
attribution. A missing duty is a gap, not a silent default.
"""

from __future__ import annotations

from typing import Any

LICENSE_URLS = {
    "CC0-1.0": "https://creativecommons.org/publicdomain/zero/1.0/",
    "CC-BY-4.0": "https://creativecommons.org/licenses/by/4.0/",
    "CC-BY-NC-4.0": "https://creativecommons.org/licenses/by-nc/4.0/",
    "MIT": "https://opensource.org/license/mit",
}

_BY = frozenset({"CC-BY-4.0", "CC-BY-NC-4.0"})


def attribution_gaps(source: dict[str, Any]) -> list[str]:
    """Names of CC duties this source does not yet satisfy."""
    license_name = str(source.get("license") or "")
    gaps: list[str] = []
    if not license_name:
        gaps.append("license")
    if not str(source.get("title") or "").strip():
        gaps.append("title")
    if not str(source.get("uri") or "").strip():
        gaps.append("uri")
    if license_name in _BY or license_name == "MIT":
        if not str(source.get("attribution") or "").strip():
            gaps.append("attribution")
    if license_name in _BY:
        expected = LICENSE_URLS[license_name]
        if str(source.get("licenseUrl") or "") != expected:
            gaps.append("licenseUrl")
        if not str(source.get("retrievedAt") or "").strip():
            gaps.append("retrievedAt")
        if not str(source.get("originSha") or "").strip():
            gaps.append("originSha")
        if not str(source.get("modificationNotice") or "").strip():
            gaps.append("modificationNotice")
    if license_name == "CC-BY-NC-4.0":
        attribution = str(source.get("attribution") or "")
        if "onco.cc" not in attribution.lower() and "data from onco" not in attribution.lower():
            # The OnCo corpus duty is the OnCo line. Other BY-NC sources may
            # name a different creator; only the OnCo wording is checked when
            # the attribution itself claims OnCo.
            pass
        if "Data from OnCo" in attribution and "onco.cc" not in attribution:
            gaps.append("onco-link")
    return gaps


def notice_complete(source: dict[str, Any]) -> bool:
    return not attribution_gaps(source)