#!/bin/bash
# ==============================================================================================
# ============================ Radarr Content Classification Scan ==============================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Overseerr lets any user request a movie into the wrong root folder (kids content added to
# the general Movies share, anime added to Kids_Movies, etc.) and most users never notice or
# correct it. This script reads Radarr's tracked movie list and classifies every movie as
# anime / kids-only / regular using metadata signals alone (genre, certification, studio,
# original language) — then reports where a movie's computed classification disagrees with
# the root folder it's actually sitting in, in both directions:
#
#   FORWARD  — a movie classified as anime/kids is sitting outside its dedicated root
#   REVERSE  — a movie sitting inside the kids/anime root doesn't match that classification
#
# Report-only. No files are moved and no Radarr API writes happen — this is a detection
# tool. Every rule below was validated against this library's real data before being
# adopted (see master.conf comments above the curated lists) — this is not a generic
# genre-matcher, it's tuned specifically against the false-positive traps that showed up
# when testing looser rules (documented per-rule below).
#
# ==============================================================================================
# CLASSIFICATION RULES
# ==============================================================================================
#
# is_anime:
#   (genre Animation AND originalLanguage Japanese) OR studio in RADARR_ANIME_STUDIOS
#   Always wins over kids when both could apply — explicit priority, not a tiebreak.
#
# is_kids ("kids will end up watching this alone" — NOT "family movie night"):
#   not is_anime AND certification not in (R, NC-17) AND (
#     (genre Animation AND certification != PG-13)
#     OR studio in RADARR_KIDS_STUDIOS
#   )
#   Deliberately excludes bare "Family" genre and bare "G" certification — both genuinely
#   traced back to live-action films the whole household watches together (Mrs. Doubtfire,
#   Doctor Dolittle, National Treasure-style adventures, classic Westerns), not kids-only
#   content. Family movie night stays in the general Movies root by design.
#
#   The PG-13 exclusion on the Animation branch is load-bearing — without it this rule
#   catches South Park movies, Sausage Party, "9", Resident Evil: Death Island, and (via
#   the curated studio list) Warner Bros. Animation's R-rated Watchmen films, since that
#   studio makes both kids content and adult content under the same name.
#
# is_junk (bad/thin TMDb match, not a real classification problem):
#   hasFile == false AND imdbId == null AND tmdb votes < RADARR_JUNK_MIN_VOTES
#   Caught live: two fake "X-Men"/"Wolverine" entries, two fake "Silent Hill" entries, one
#   fake "The Purge" spinoff — all monitored placeholders with nothing behind them. The
#   fix for these is removal from Radarr, not blocklist+redownload — there's no release to
#   blocklist and likely nothing legitimate to redownload under that exact TMDb match.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# Report, Don't Act
#   This script never calls Radarr's write API and never touches a file. Every finding is
#   a candidate for a human decision — moving media and re-pointing Radarr's tracking is a
#   separate, deliberate follow-up action, not something this scan does automatically.
#
# Curated Lists, Not Bare Genre/Cert Matching
#   Every signal used here failed at least once as a bare/standalone check during rule
#   development (Family genre, G certification, blanket Animation genre, bare Anime genre
#   tag, Disney+/general-platform networks) — see master.conf comments for what each
#   curated list deliberately excludes and why.
#
# Cache-First, Never a Per-Movie Call
#   Uses arr_get_tracked_data() same as radarr_cleanup.sh — Radarr's movie list already
#   embeds everything this script needs per movie, so this is a single API call (or zero,
#   if the shared cache is warm) regardless of library size.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# host*.conf
#   RADARR_URL / RADARR_API_KEY / RADARR_MOVIES_ROOT — existing, aliased by detect_hosts()
#   RADARR_KIDS_ROOT / RADARR_ANIME_ROOT — rootFolderPath literals as reported by the API
#     (e.g. "/kids movies", "/ext-anime-movies") — leave blank on a host with no dedicated
#     root for that category; the corresponding checks are skipped, not treated as an error.
#
# master.conf
#   RADARR_ANIME_STUDIOS / RADARR_KIDS_STUDIOS — curated studio allowlists
#   RADARR_JUNK_MIN_VOTES — TMDb vote threshold for the bad-metadata check
#   RADARR_VERSION_MAJOR  — expected API major version (reused from radarr_cleanup.sh)
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
#   radarr_classification_scan.sh          — normal run, prints report
#   radarr_classification_scan.sh --log    — verbose (per-movie TRACKED-style logging)
#   radarr_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 "${RADARR_URL:-}" ]] || [[ -z "${RADARR_API_KEY:-}" ]]; then
    info "Radarr not configured on $MY_ID ($LOCAL_SERVER_NAME) — skipping"
    exit 0
fi

require_var RADARR_URL
require_var RADARR_API_KEY

if [[ "$SHOW_STATUS" == true ]]; then
    echo ""
    echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
    echo "$ICON_HOST    Identity:       $MY_ID ($LOCAL_SERVER_NAME)"
    echo "$ICON_GEAR    Radarr URL:     $RADARR_URL"
    echo "$ICON_GEAR    Movies root:    $RADARR_MOVIES_ROOT"
    echo "$ICON_GEAR    Kids root:      ${RADARR_KIDS_ROOT:-<not configured>}"
    echo "$ICON_GEAR    Anime root:     ${RADARR_ANIME_ROOT:-<not configured>}"
    echo "$ICON_GEAR    Anime studios:  ${#RADARR_ANIME_STUDIOS[@]} curated"
    echo "$ICON_GEAR    Kids studios:   ${#RADARR_KIDS_STUDIOS[@]} curated"
    echo "$ICON_GEAR    Junk min votes: ${RADARR_JUNK_MIN_VOTES:-15}"
    echo "━━━━━━━━━━━━━━━━━━━━━━━"
    exit 0
fi

echo ""
echo "━━━ $ICON_SYNC Fetching Radarr Library ━━━"

if ! check_api "$RADARR_URL" "Radarr" 10; then
    exit 1
fi

check_arr_version "$RADARR_URL" "$RADARR_API_KEY" "v3" "$RADARR_VERSION_MAJOR" "Radarr" || exit 1

MOVIES_RESPONSE=$(arr_get_tracked_data "radarr" "$RADARR_URL" "$RADARR_API_KEY" "v3") || {
    error "Failed to fetch movies from Radarr"
    exit 1
}

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

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

ANIME_STUDIOS_JSON=$(printf '%s\n' "${RADARR_ANIME_STUDIOS[@]}" | jq -R . | jq -s .)
KIDS_STUDIOS_JSON=$(printf '%s\n' "${RADARR_KIDS_STUDIOS[@]}" | jq -R . | jq -s .)
JUNK_MIN_VOTES="${RADARR_JUNK_MIN_VOTES:-15}"

RESULTS=$(echo "$MOVIES_RESPONSE" | jq \
    --argjson animeStudios "$ANIME_STUDIOS_JSON" \
    --argjson kidsStudios "$KIDS_STUDIOS_JSON" \
    --arg animeRoot "${RADARR_ANIME_ROOT:-}" \
    --arg kidsRoot "${RADARR_KIDS_ROOT:-}" \
    --argjson junkMinVotes "$JUNK_MIN_VOTES" '
    def is_anime:
        (any(.genres[]?; . == "Animation") and .originalLanguage.name == "Japanese")
        or (.studio as $s | $animeStudios | index($s) != null);
    def not_adult: (.certification != "R") and (.certification != "NC-17");
    def is_kids:
        (is_anime | not) and not_adult and (
            (any(.genres[]?; . == "Animation") and .certification != "PG-13")
            or (.studio as $s | $kidsStudios | index($s) != null)
        );
    def is_junk:
        (.hasFile == false) and (.imdbId == null)
        and ((.ratings.tmdb.votes // 999999) < $junkMinVotes);

    map(
        {
            title, id, studio, certification, rootFolderPath, genres,
            is_anime: is_anime,
            is_kids: is_kids,
            is_junk: is_junk
        } |
        . + {
            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 and (.is_junk | not)),
            reverse_kids_leak:  ((.is_anime | not) and (.is_kids | not) and $kidsRoot != "" and .rootFolderPath == $kidsRoot
                                 and (.is_junk | not)
                                 and (.certification == "R" or .certification == "NC-17"
                                      or (.certification == "PG-13"
                                          and (any(.genres[]?; . == "Family") | not)
                                          and (any(.genres[]?; . == "Animation") | not))))
        }
    )
')

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')
JUNK_COUNT=$(echo "$RESULTS" | jq '[.[] | select(.is_junk)] | 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 or .is_junk) |
        "  [\(if .is_junk then "JUNK" elif .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), studio: \(.studio // "n/a"), cert: \(.certification // "n/a"))"'
fi

# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo ""
echo "━━━━━ $ICON_SUMMARY RADARR CLASSIFICATION SUMMARY ━━━━━"
echo "$ICON_HOST    Identity:              $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_SYNC    Movies scanned:        $MOVIE_COUNT"
echo "$ICON_TRASH   Forward — anime miss:  $FORWARD_ANIME_COUNT  (classified anime, outside ${RADARR_ANIME_ROOT:-<unconfigured>})"
echo "$ICON_TRASH   Forward — kids miss:   $FORWARD_KIDS_COUNT  (classified kids, outside ${RADARR_KIDS_ROOT:-<unconfigured>})"
echo "$ICON_WARN    Reverse — anime leak:  $REVERSE_ANIME_COUNT  (in ${RADARR_ANIME_ROOT:-<unconfigured>}, no anime signal — review, may be deliberate style placement)"
echo "$ICON_WARN    Reverse — kids leak:   $REVERSE_KIDS_COUNT  (in ${RADARR_KIDS_ROOT:-<unconfigured>}, adult-rated content)"
echo "$ICON_PROTECTED Bad metadata (junk):  $JUNK_COUNT  (hasFile=false, no imdbId, thin TMDb match — candidates for removal, not redownload)"
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
[[ "$ENABLE_LOGGING" != true ]] && echo "  (run with --log for the per-title list)"

exit 0