# cf_voice/privacy.py — local acoustic privacy risk scoring
#
# MIT licensed. Never transmitted to cloud. Never logged server-side.
#
# Derives a privacy_risk level (low / moderate / high) from the combined
# acoustic fingerprint: scene + environ labels + speaker type + accent.
#
# Design rationale (#20):
#   - "outdoor_urban" + "crowd_chatter" + "traffic" → low: clearly public
#   - "indoor_quiet" + "background_voices"           → moderate: conversation overheard
#   - "outdoor_nature" + "birdsong" + regional accent → moderate-high: location-identifying compound
#   - "indoor_quiet" + no background voices          → low
#
# Risk gates (Linnet):
#   high:     warn before sending audio chunk to cloud STT; offer local-only fallback
#   moderate: attach privacy_flags to session state, no blocking action
#   low:      proceed normally
from __future__ import annotations

from dataclasses import dataclass, field
from typing import Literal

PrivacyLevel = Literal["low", "moderate", "high"]


@dataclass
class PrivacyRisk:
    """
    Locally-computed privacy risk for a single audio window.

    level:       aggregate risk level
    flags:       ordered list of contributing signal descriptions
    """
    level: PrivacyLevel
    flags: list[str] = field(default_factory=list)


# ── Signal sets ───────────────────────────────────────────────────────────────

_PUBLIC_SCENES = {"outdoor_urban", "public_transit"}
_NATURE_SCENES = {"outdoor_nature"}
_QUIET_SCENES = {"indoor_quiet"}

_LOCATION_ENVIRON = {"birdsong", "wind", "rain", "water"}
_URBAN_ENVIRON = {"traffic", "crowd_chatter", "street_signal", "construction"}


def score_privacy_risk(
    scene: str | None,
    environ_labels: list[str],
    speaker: str | None,
    accent: str | None,
) -> PrivacyRisk:
    """
    Derive a PrivacyRisk from the current acoustic fingerprint.

    All inputs are nullable — this function handles partial signals gracefully.
    Called per audio window; results are never persisted or transmitted.

    Args:
        scene:          SCENE_LABEL string or None
        environ_labels: list of ENVIRON_LABEL strings active in this window
        speaker:        SPEAKER_LABEL string or None
        accent:         ACCENT_LABEL string or None (None when CF_VOICE_ACCENT disabled)
    """
    flags: list[str] = []
    score = 0  # internal accumulator; maps to level at the end

    environ_set = set(environ_labels)

    # ── Clearly public environments → reduce risk ─────────────────────────────
    if scene in _PUBLIC_SCENES or environ_set & _URBAN_ENVIRON:
        flags.append("public_environment")
        score -= 1

    # ── Background voices: conversation may be overheard ─────────────────────
    if speaker == "background_voices":
        flags.append("background_voices_detected")
        score += 2

    # ── Quiet indoor: no background noise reduces identifiability ────────────
    if scene in _QUIET_SCENES and speaker not in ("background_voices", "human_multi"):
        flags.append("controlled_environment")
        # No score change — neutral

    # ── Nature sounds: alone they suggest a quiet, potentially identifiable location
    nature_match = environ_set & _LOCATION_ENVIRON
    if nature_match:
        flags.append(f"location_signal: {', '.join(sorted(nature_match))}")
        score += 1

    # ── Nature scene + nature sounds: compound location-identifying signal ────
    if scene in _NATURE_SCENES and nature_match:
        flags.append("compound_location_signal")
        score += 1

    # ── Regional accent + nature: narrows location to region + environment ────
    if accent and accent not in ("en_us", "other") and nature_match:
        flags.append(f"accent_plus_location: {accent}")
        score += 1

    # ── Quiet indoor + background voices: overheard conversation ─────────────
    if scene in _QUIET_SCENES and speaker == "background_voices":
        flags.append("overheard_conversation")
        score += 1

    # ── Map score to level ────────────────────────────────────────────────────
    if score <= 0:
        level: PrivacyLevel = "low"
    elif score <= 2:
        level = "moderate"
    else:
        level = "high"

    return PrivacyRisk(level=level, flags=flags)