#!/bin/bash
# ==============================================================================================
# ============================ Sonarr Content Classification Scan ==============================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Same problem as radarr_classification_scan.sh, TV side: Overseerr lets any user request a
# show into the wrong root folder (kids shows added to the general TV share, anime added to
# Kids_Tv_Shows, etc.). This script reads Sonarr's tracked series list and classifies every
# series as anime / kids-only / regular using metadata signals alone (genre, certification,
# network, original language) — then reports where a series' computed classification
# disagrees with the root folder it's actually sitting in, in both directions:
#
#   FORWARD  — a series classified as anime/kids is sitting outside its dedicated root
#   REVERSE  — a series sitting inside the kids/anime root doesn't match that classification
#
# Report-only. No files are moved and no Sonarr API writes happen. Every rule below was
# validated against this library's real data before being adopted — see the companion
# comment block in master.conf above the curated lists.
#
# ==============================================================================================
# CLASSIFICATION RULES — DIFFERENT FIELD MODEL THAN RADARR, NOT A COPY-PASTE
# ==============================================================================================
#
# TV metadata (TheTVDB, via Sonarr) shapes these signals differently than movie metadata
# (TMDb, via Radarr) — every difference below was confirmed live, not assumed:
#   - Sonarr has an explicit "Anime" genre tag; Radarr does not.
#   - Sonarr uses a single "network" field (TheTVDB's broadcaster), not "studio".
#   - Certification is on the US TV Parental Guidelines scale (TV-Y/TV-Y7/TV-G/TV-PG/
#     TV-14/TV-MA), not the MPAA scale — the tiers do not mean the same thing at the same
#     position (TV-G is "general audience", not "for children", unlike movie G).
#
# is_anime:
#   genre "Anime" (corroborated by Japanese language OR a Japan network — the bare tag alone
#     produced a real false positive: "Craig of the Creek", an all-American Cartoon Network
#     show, carries an "Anime" genre tag on TheTVDB for no discernible reason)
#   OR (genre Animation AND originalLanguage Japanese)
#   OR network in SONARR_ANIME_NETWORKS
#   Always wins over kids when both could apply — explicit priority, not a tiebreak.
#
# is_kids ("kids will end up watching this alone" — NOT "family show night"):
#   not is_anime AND (
#     genre "Children"                      (NOT "Family" — see below)
#     OR certification in (TV-Y, TV-Y7)     (NOT TV-G — see below)
#     OR network in SONARR_KIDS_NETWORKS
#   )
#   "Family" genre and "TV-G" certification were both tested standalone and rejected —
#   both catch general-audience live-action content the whole household watches together
#   (I Love Lucy, The Brady Bunch, Full House, Homestead Rescue), not kids-only content.
#   Blanket "Animation" genre was also tested and rejected — it's dominated on TV by adult
#   animated sitcoms (Rick and Morty, BoJack Horseman, Family Guy, South Park), unlike the
#   movie side where it's a usable (gated) signal.
#
# No junk-detection tier here (unlike Radarr) — TheTVDB's ratings/imdbId data is far
# sparser than TMDb's even for completely legitimate shows (confirmed live: "The Pussycat
# Dolls Present: The Search for the Next Doll", a real 2007 MTV show, has ratings.votes=0
# and imdbId=null) — the vote-count heuristic that works for Radarr would flag real content
# for removal here, so it's deliberately not reused.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# Report, Don't Act — same as the Radarr scan; moving/re-pointing is a deliberate follow-up.
# Curated Lists, Not Bare Genre/Cert Matching — see master.conf comments for exclusions.
# Cache-First — arr_get_tracked_data() same as sonarr_cleanup.sh, single call regardless
#   of library size.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# host*.conf
#   SONARR_URL / SONARR_API_KEY / SONARR_TV_ROOT — existing, aliased by detect_hosts()
#   SONARR_KIDS_ROOT / SONARR_ANIME_ROOT — rootFolderPath literals as reported by the API
#     (e.g. "/kids tv", "/ext-anime-shows") — leave blank on a host with no dedicated root
#     for that category; the corresponding checks are skipped, not treated as an error.
#
# master.conf
#   SONARR_ANIME_NETWORKS / SONARR_KIDS_NETWORKS — curated network allowlists
#   SONARR_VERSION_MAJOR — expected API major version (reused from sonarr_cleanup.sh)
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
#   sonarr_classification_scan.sh          — normal run, prints report
#   sonarr_classification_scan.sh --log    — verbose (per-series list)
#   sonarr_classification_scan.sh --status — show config and exit
#
# ==============================================================================================

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"

source "$SCRIPT_DIR/../load_config.sh"

parse_args "$@"

# ==============================================================================================
# ━━━ Setup ━━━
# ==============================================================================================
if [[ "$EUID" -ne 0 ]]; then
    error "Must be run as root"
    exit 1
fi

if ! command -v jq >/dev/null 2>&1; then
    error "jq not found — required for JSON parsing"
    exit 1
fi

detect_hosts

if [[ -z "${SONARR_URL:-}" ]] || [[ -z "${SONARR_API_KEY:-}" ]]; then
    info "Sonarr not configured on $MY_ID ($LOCAL_SERVER_NAME) — skipping"
    exit 0
fi

require_var SONARR_URL
require_var SONARR_API_KEY

if [[ "$SHOW_STATUS" == true ]]; then
    echo ""
    echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
    echo "$ICON_HOST    Identity:        $MY_ID ($LOCAL_SERVER_NAME)"
    echo "$ICON_GEAR    Sonarr URL:      $SONARR_URL"
    echo "$ICON_GEAR    TV root:         $SONARR_TV_ROOT"
    echo "$ICON_GEAR    Kids root:       ${SONARR_KIDS_ROOT:-<not configured>}"
    echo "$ICON_GEAR    Anime root:      ${SONARR_ANIME_ROOT:-<not configured>}"
    echo "$ICON_GEAR    Anime networks:  ${#SONARR_ANIME_NETWORKS[@]} curated"
    echo "$ICON_GEAR    Kids networks:   ${#SONARR_KIDS_NETWORKS[@]} curated"
    echo "━━━━━━━━━━━━━━━━━━━━━━━"
    exit 0
fi

echo ""
echo "━━━ $ICON_SYNC Fetching Sonarr Library ━━━"

if ! check_api "$SONARR_URL" "Sonarr" 10; then
    exit 1
fi

check_arr_version "$SONARR_URL" "$SONARR_API_KEY" "v3" "$SONARR_VERSION_MAJOR" "Sonarr" || exit 1

SERIES_RESPONSE=$(arr_get_tracked_data "sonarr" "$SONARR_URL" "$SONARR_API_KEY" "v3") || {
    error "Failed to fetch series from Sonarr"
    exit 1
}

SERIES_COUNT=$(echo "$SERIES_RESPONSE" | jq -r 'length' 2>/dev/null)
if [[ -z "$SERIES_COUNT" ]] || [[ "$SERIES_COUNT" -eq 0 ]]; then
    error "API returned 0 series — aborting"
    exit 1
fi
info "$SERIES_COUNT series loaded"

# ==============================================================================================
# ━━━ Classify ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_CLEAN Classifying ━━━"

ANIME_NETWORKS_JSON=$(printf '%s\n' "${SONARR_ANIME_NETWORKS[@]}" | jq -R . | jq -s .)
KIDS_NETWORKS_JSON=$(printf '%s\n' "${SONARR_KIDS_NETWORKS[@]}" | jq -R . | jq -s .)
# Not just the US TV-MA/TV-14 tiers — non-US certification scales use different labels for the
# same "clearly adult" tier (confirmed live: "Tomb Raider: The Legend of Lara Croft" is "16+").
ADULT_CERT_JSON='["TV-MA","TV-14","MA15+","16","16+","18","15","14"]'

RESULTS=$(echo "$SERIES_RESPONSE" | jq \
    --argjson animeNetworks "$ANIME_NETWORKS_JSON" \
    --argjson kidsNetworks "$KIDS_NETWORKS_JSON" \
    --argjson adultCert "$ADULT_CERT_JSON" \
    --arg animeRoot "${SONARR_ANIME_ROOT:-}" \
    --arg kidsRoot "${SONARR_KIDS_ROOT:-}" '
    def is_anime:
        (any(.genres[]?; . == "Anime")
            and (.originalLanguage.name == "Japanese" or (.network as $n | $animeNetworks | index($n) != null)))
        or (any(.genres[]?; . == "Animation") and .originalLanguage.name == "Japanese")
        or (.network as $n | $animeNetworks | index($n) != null);
    def is_kids:
        (is_anime | not) and (
            any(.genres[]?; . == "Children")
            or (.certification as $c | ["TV-Y","TV-Y7"] | index($c) != null)
            or (.network as $n | $kidsNetworks | index($n) != null)
        );

    map(
        {
            title, id, network, certification, rootFolderPath,
            is_anime: is_anime,
            is_kids: is_kids
        } |
        . + {
            forward_anime_miss: (.is_anime and $animeRoot != "" and .rootFolderPath != $animeRoot),
            forward_kids_miss:  (.is_kids  and $kidsRoot  != "" and .rootFolderPath != $kidsRoot),
            reverse_anime_leak: ((.is_anime | not) and $animeRoot != "" and .rootFolderPath == $animeRoot),
            reverse_kids_leak:  ((.is_anime | not) and (.is_kids | not) and $kidsRoot != "" and .rootFolderPath == $kidsRoot
                                 and (.certification as $c | $adultCert | index($c) != null))
        }
    )
')

FORWARD_ANIME_COUNT=$(echo "$RESULTS" | jq '[.[] | select(.forward_anime_miss)] | length')
FORWARD_KIDS_COUNT=$(echo "$RESULTS" | jq '[.[] | select(.forward_kids_miss)] | length')
REVERSE_ANIME_COUNT=$(echo "$RESULTS" | jq '[.[] | select(.reverse_anime_leak)] | length')
REVERSE_KIDS_COUNT=$(echo "$RESULTS" | jq '[.[] | select(.reverse_kids_leak)] | length')

if [[ "$ENABLE_LOGGING" == true ]]; then
    echo "$RESULTS" | jq -r '.[] | select(.forward_anime_miss or .forward_kids_miss or .reverse_anime_leak or .reverse_kids_leak) |
        "  [\(if .forward_anime_miss then "FORWARD-ANIME" elif .forward_kids_miss then "FORWARD-KIDS" elif .reverse_anime_leak then "REVERSE-ANIME" elif .reverse_kids_leak then "REVERSE-KIDS" else "?" end)] \(.title) (root: \(.rootFolderPath), network: \(.network // "n/a"), cert: \(.certification // "n/a"))"'
fi

# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo ""
echo "━━━━━ $ICON_SUMMARY SONARR CLASSIFICATION SUMMARY ━━━━━"
echo "$ICON_HOST    Identity:              $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_SYNC    Series scanned:        $SERIES_COUNT"
echo "$ICON_TRASH   Forward — anime miss:  $FORWARD_ANIME_COUNT  (classified anime, outside ${SONARR_ANIME_ROOT:-<unconfigured>})"
echo "$ICON_TRASH   Forward — kids miss:   $FORWARD_KIDS_COUNT  (classified kids, outside ${SONARR_KIDS_ROOT:-<unconfigured>})"
echo "$ICON_WARN    Reverse — anime leak:  $REVERSE_ANIME_COUNT  (in ${SONARR_ANIME_ROOT:-<unconfigured>}, no anime signal — review, may be deliberate style placement)"
echo "$ICON_WARN    Reverse — kids leak:   $REVERSE_KIDS_COUNT  (in ${SONARR_KIDS_ROOT:-<unconfigured>}, adult-rated content)"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
[[ "$ENABLE_LOGGING" != true ]] && echo "  (run with --log for the per-title list)"

exit 0