#!/bin/bash
# ==============================================================================================
# ================================= Sonarr Cleanup =============================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Delete orphaned TV episode files not tracked by Sonarr. Queries the API for
# all tracked episode file paths, walks the library on disk, and removes anything
# untracked that is old enough to be past the import window. Triggers an Emby
# library clean after each deletion run so ghost entries disappear immediately.
#
# ==============================================================================================
# OPERATIONAL MODEL
# ==============================================================================================
#
# Every file encountered on disk is classified into one of five categories:
#
#   TRACKED   — Sonarr API knows this exact path → leave it alone
#   PROTECTED — matches SONARR_PROTECTED_PATTERNS → never delete
#   ORPHAN    — video file, not tracked, older than SONARR_ORPHAN_AGE → delete
#   JUNK      — not a video extension, not protected → delete regardless of age
#   RECENT    — not tracked, under SONARR_ORPHAN_AGE → skip (may be mid-import)
#
# Sonarr generates show artwork (*.jpg), metadata (*.nfo), and manages subtitles
# (*.srt, *.sub, *.ass) but does NOT include these in its tracked file API response.
# Without PROTECTED classification these would be deleted — breaking Sonarr and
# Emby metadata display.
#
# After deletions: notify_emby_scan() triggers Emby "Clean Missing Files" task.
# Emby removes ghost entries immediately — no user-facing file-not-found errors.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# API as Ground Truth
#   What Sonarr tracks is authoritative. Files not in the API response are
#   orphans — Sonarr has no record of them and they serve no purpose.
#   The script never infers ownership from directory structure alone.
#
# Age Gate Before Deletion
#   Files under SONARR_ORPHAN_AGE are left alone regardless of tracked status.
#   Sonarr's import pipeline writes files before registering them — acting
#   immediately would delete files mid-import.
#
# Emby Cleanup Is Part of the Job
#   Deleting a file without telling Emby leaves ghost entries that show as
#   broken items. Triggering the Emby clean is not optional — it completes
#   the deletion from the user's perspective.
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Seven gates — ALL must pass before any file is touched:
#   1. Container running and not starting/unhealthy
#   2. API reachable
#   3. API version matches SONARR_VERSION_MAJOR in master.conf
#   4. Series count > 0
#   5. Tracked file count > 0
#   6. Tracked count >= SONARR_MIN_TRACKED_PCT % of last known count
#   7. Deletion size < SONARR_MAX_DELETE_GB — or --i-know-what-im-doing required
#
#   acquire_lock "wait"  — large scans take time, wait for previous run to finish
#   jq + curl validation — exits if either tool missing
#   ARR_DOCKER_TIMEOUT   — container checks protected against daemon hangs (script-local, not common.sh's DOCKER_TIMEOUT)
#   notify_emby_scan()   — triggers Emby clean after deletion
#   platform_require_cmd  — notify script validated before use
#   Silent by default    — orphans/junk warn(), clean library logs silently
#
# ==============================================================================================
# STATE FILES
# ==============================================================================================
#
#   SONARR_TRACKED_COUNT_FILE — persistent baseline for the tracked % safety check (gate 6)
#       Updated after each successful run. Protects against misconfigured root path
#       returning an empty API response and deleting the entire library.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# host*.conf
#
#   HOST*_SONARR_URL / HOST*_SONARR_API_KEY / HOST*_SONARR_TV_ROOT
#   HOST*_SONARR_PATH_MAP — container path → host path translation
#   All aliased by detect_hosts() — script uses unprefixed names
#
# master.conf
#
#   SONARR_ORPHAN_AGE          — days before untracked file eligible for deletion
#   SONARR_MAX_DELETE_GB       — require --i-know-what-im-doing above this
#   SONARR_MIN_TRACKED_PCT     — abort if tracked count drops below this % of last run
#   SONARR_TRACKED_COUNT_FILE  — persistent baseline file path
#   SONARR_EXTENSIONS          — video file extensions for orphan classification
#   SONARR_PROTECTED_PATTERNS  — file patterns never deleted
#   SONARR_VERSION_MAJOR       — expected Sonarr major version for API safety check
#   SONARR_IMPORT_SCAN_TIMEOUT — seconds to wait for pre-flight import scan (default 600)
#   ARR_CLEANUP_STATS          — stats file path (read by coffee report)
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
#   sonarr_cleanup.sh                                           — normal run
#   sonarr_cleanup.sh --dry-run                                 — preview, no deletions
#   sonarr_cleanup.sh --log                                     — verbose output
#   sonarr_cleanup.sh --status                                  — show config and exit
#   sonarr_cleanup.sh --i-know-what-im-doing                    — bypass size threshold
#   sonarr_cleanup.sh --i-know-what-im-doing --skip-age-check — NUCLEAR MODE
#
# NUCLEAR MODE: both flags bypass age check AND size threshold. User accepts full
# responsibility — the flag name is long and annoying by design.
#
# ==============================================================================================

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

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

# ── Special flag pre-processing ───────────────────────────────────────────────────────────────
parse_destructive_flags "$@"

parse_args "${FILTERED_ARGS[@]}"

# ── Nuclear mode warning ──────────────────────────────────────────────────────────────────────
nuclear_mode_warning

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

if ! command -v curl >/dev/null 2>&1; then
    error "curl not found — required for Sonarr API calls"
    exit 1
fi

if ! command -v jq >/dev/null 2>&1; then
    error "jq not found — required for JSON parsing"
    notify "Sonarr cleanup failed on $(hostname) — jq not installed" "Sonarr Cleanup" "warning"
    exit 1
fi


acquire_lock "wait"
TMP_DIR="/tmp/sonarr_cleanup_$$"
mkdir -p "$TMP_DIR"
trap "_release_all_locks; rm -rf $TMP_DIR" EXIT

if ! command -v docker &>/dev/null; then
    error "Docker command not found"
    exit 1
fi

# detect_hosts() sets MY_ID and aliases SONARR_URL, SONARR_API_KEY, SONARR_TV_ROOT
detect_hosts

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

ARR_DOCKER_TIMEOUT=15
SONARR_CONTAINER="Sonarr"

# Build path map from MY_ID's Sonarr path map
build_arr_path_map "SONARR"

require_var SONARR_URL
require_var SONARR_API_KEY
require_var SONARR_TV_ROOT

if [[ ! -d "$SONARR_TV_ROOT" ]]; then
    error "TV root not found: $SONARR_TV_ROOT"
    notify "Sonarr cleanup failed on $(hostname) — TV root not found: $SONARR_TV_ROOT" \
        "Sonarr Cleanup" "warning"
    exit 1
fi

log "$ICON_GEAR Config: url=${SONARR_URL} root=${SONARR_TV_ROOT}"
echo "  $MY_ID ($LOCAL_SERVER_NAME) — $SONARR_URL"

[[ "$DRY_RUN" == true ]]      && warn "DRY RUN — no files will be deleted"
[[ "$I_KNOW" == true ]]       && warn "OVERRIDE — --i-know-what-im-doing active"
[[ "$SKIP_AGE_CHECK" == true ]] && warn "OVERRIDE — --skip-age-check active — age check bypassed"

# ==============================================================================================
# ━━━ Status ━━━
# ==============================================================================================
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_TIME    Orphan age:         ${SONARR_ORPHAN_AGE} days"
    echo "$ICON_GEAR    Max delete:         ${SONARR_MAX_DELETE_GB}GB (requires --i-know-what-im-doing)"
    echo "$ICON_GEAR    Min tracked %:      ${SONARR_MIN_TRACKED_PCT}%"
    echo "$ICON_GEAR    Sonarr ver:         v${SONARR_VERSION_MAJOR} expected"
    echo "$ICON_GEAR    Extensions:         ${SONARR_EXTENSIONS[*]}"
    echo "$ICON_GEAR    Protected patterns: ${SONARR_PROTECTED_PATTERNS[*]}"
    echo "$ICON_GEAR    Dry Run:            $DRY_RUN"
    echo "$ICON_GEAR    I know:             $I_KNOW"
    echo "$ICON_GEAR    Skip age check:     $SKIP_AGE_CHECK"
    echo "━━━━━━━━━━━━━━━━━━━━━━━"
    exit 0
fi

# ==============================================================================================
# ━━━ Safety Layer 1 — Container Health ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_SHIELD Safety Checks ━━━"

check_container_health "$SONARR_CONTAINER" "$ARR_DOCKER_TIMEOUT" "Sonarr Cleanup"

# ==============================================================================================
# ── HELPER FUNCTIONS ──────────────────────────────────────────────────────────────────────────
# ==============================================================================================

# check_container_health(), arr_api(), has_extension(), matches_pattern_list(), format_bytes() — common.sh

# ==============================================================================================
# ━━━ Pre-flight: Sonarr Import Scan ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_SYNC Pre-flight: Sonarr Import Scan ━━━"

# Fetch root folders from Sonarr API and translate container paths to host paths
mapfile -t SCAN_ROOTS < <(
    arr_api "$SONARR_URL" "$SONARR_API_KEY" "v3" "rootfolder" "Sonarr" | \
    jq -r '.[].path' 2>/dev/null | \
    while IFS= read -r cp; do translate_path "$cp"; done
)

if [[ "${#SCAN_ROOTS[@]}" -eq 0 ]]; then
    error "No root folders returned from Sonarr API — aborting"
    notify "Sonarr cleanup aborted on $(hostname) — no root folders from API" \
        "Sonarr Cleanup" "warning"
    exit 1
fi

info "Scan targets (${#SCAN_ROOTS[@]}): ${SCAN_ROOTS[*]}"

info "Triggering ProcessMonitoredDownloads pre-flight"
SCAN_PAYLOAD='{"name": "ProcessMonitoredDownloads"}'

trigger_and_await_command "$SONARR_URL" "$SONARR_API_KEY" "v3" "$SCAN_PAYLOAD" "${SONARR_IMPORT_SCAN_TIMEOUT:-600}"

# ==============================================================================================
# ━━━ Fetch Sonarr Tracked Files ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_SYNC Fetching Sonarr Tracked Files ━━━"

# Safety Layer 2 — API reachability
if ! check_api "$SONARR_URL" "Sonarr" 10; then
    notify "Sonarr cleanup aborted on $(hostname) — API unreachable" "Sonarr Cleanup" "warning"
    exit 1
fi

# Safety Layer 3 — API version check
check_arr_version "$SONARR_URL" "$SONARR_API_KEY" "v3" "$SONARR_VERSION_MAJOR" "Sonarr" || exit 1

info "Querying Sonarr API..."

# Fetch all series
SERIES_RESPONSE=$(arr_api "$SONARR_URL" "$SONARR_API_KEY" "v3" "series" "Sonarr") || {
    error "Failed to fetch series from Sonarr"
    notify "Sonarr cleanup failed on $(hostname) — could not fetch series" \
        "Sonarr Cleanup" "warning"
    exit 1
}

SERIES_IDS=$(echo "$SERIES_RESPONSE" | jq -r '.[].id' 2>/dev/null)
SERIES_COUNT=$(echo "$SERIES_IDS" | grep -c "." 2>/dev/null || echo 0)

# Safety Layer 4 — series count > 0
if [[ "$SERIES_COUNT" -eq 0 ]]; then
    error "API returned 0 series — aborting to prevent mass deletion"
    notify "Sonarr cleanup aborted on $(hostname) — 0 series returned" \
        "Sonarr Cleanup" "warning"
    exit 1
fi

info "Found $SERIES_COUNT series — fetching episode files..."

TRACKED_FILE="$TMP_DIR/tracked_paths.txt"
> "$TRACKED_FILE"

SERIES_INDEX=0
while IFS= read -r series_id; do
    [[ -z "$series_id" ]] && continue
    (( SERIES_INDEX++ ))
    [[ $(( SERIES_INDEX % 50 )) -eq 0 ]] && \
        log "Fetching files: $SERIES_INDEX/$SERIES_COUNT series..."
    SERIES_FILES=$(arr_api "$SONARR_URL" "$SONARR_API_KEY" "v3" "episodefile?seriesId=${series_id}" "Sonarr" 2>/dev/null)
    if [[ -n "$SERIES_FILES" ]]; then
        while IFS= read -r api_path; do
            [[ -z "$api_path" ]] && continue
            translate_path "$api_path" >> "$TRACKED_FILE"
        done < <(echo "$SERIES_FILES" | jq -r '.[].path' 2>/dev/null)
    fi
done <<< "$SERIES_IDS"

sort -u "$TRACKED_FILE" -o "$TRACKED_FILE"

# Build in-memory lookup map — O(1) per lookup vs O(n) grep per file
declare -A TRACKED_MAP
while IFS= read -r _tracked_path; do
    [[ -n "$_tracked_path" ]] && TRACKED_MAP["$_tracked_path"]=1
done < "$TRACKED_FILE"
unset _tracked_path
info "Built in-memory lookup map: ${#TRACKED_MAP[@]} tracked paths"
TRACKED_COUNT=$(wc -l < "$TRACKED_FILE")

# Safety Layer 5 — tracked count > 0
if [[ "$TRACKED_COUNT" -eq 0 ]]; then
    error "API returned 0 tracked files — aborting to prevent mass deletion"
    notify "Sonarr cleanup aborted on $(hostname) — 0 tracked files returned" \
        "Sonarr Cleanup" "warning"
    exit 1
fi

info "$SERIES_COUNT series | $TRACKED_COUNT tracked episode files"

# Safety Layer 6 — percentage drop vs last known count
check_tracked_count_floor "$TRACKED_COUNT" "$SONARR_TRACKED_COUNT_FILE" "$SONARR_MIN_TRACKED_PCT" "Sonarr Cleanup"

# ==============================================================================================
# ━━━ Scan TV Root ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_CLEAN Scanning TV Root ━━━"
info "Root: $SONARR_TV_ROOT | Orphan age: ${SONARR_ORPHAN_AGE} days"

START=$(date +%s)
ORPHAN_COUNT=0
JUNK_COUNT=0
RECENT_COUNT=0
PROTECTED_COUNT=0
ORPHAN_BYTES=0
JUNK_BYTES=0

AGE_SECONDS=$(( SONARR_ORPHAN_AGE * 86400 ))
NOW=$(date +%s)

while IFS= read -r filepath; do
    [[ -z "$filepath" ]] && continue

    if [[ -n "${TRACKED_MAP[$filepath]:-}" ]]; then
        log "TRACKED: $filepath"
        continue
    fi

    if matches_pattern_list "$filepath" "${SONARR_PROTECTED_PATTERNS[@]}"; then
        log "$ICON_PROTECTED PROTECTED: $filepath"
        (( PROTECTED_COUNT++ ))
        continue
    fi

    FILE_SIZE=$(stat -c%s "$filepath" 2>/dev/null || echo 0)

    if has_extension "$filepath" "${SONARR_EXTENSIONS[@]}"; then
        FILE_MTIME=$(stat -c %Y "$filepath" 2>/dev/null || echo 0)
        FILE_AGE=$(( NOW - FILE_MTIME ))

        if [[ "$FILE_AGE" -lt "$AGE_SECONDS" ]] && [[ "$SKIP_AGE_CHECK" != true ]]; then
            log "RECENT (skipping): $filepath"
            (( RECENT_COUNT++ ))
            continue
        fi

        warn "$ICON_TRASH ORPHAN: $filepath"
        (( ORPHAN_COUNT++ ))
        ORPHAN_BYTES=$(( ORPHAN_BYTES + FILE_SIZE ))
    else
        log "JUNK: $filepath"
        (( JUNK_COUNT++ ))
        JUNK_BYTES=$(( JUNK_BYTES + FILE_SIZE ))
    fi

done < <(
    for host_path in "${SCAN_ROOTS[@]}"; do
        [[ -d "$host_path" ]] && find "$host_path" -type f 2>/dev/null
    done | sort -u
)

TOTAL_DELETE_BYTES=$(( ORPHAN_BYTES + JUNK_BYTES ))
TOTAL_REMOVED=$(( ORPHAN_COUNT + JUNK_COUNT ))

# ==============================================================================================
# ━━━ Safety Layer 7 — Deletion Size Threshold ━━━
# ==============================================================================================
check_delete_size_threshold "$TOTAL_DELETE_BYTES" "$SONARR_MAX_DELETE_GB" "Sonarr Cleanup"

# ── Execute Deletions ─────────────────────────────────────────────────────────────────────────
if [[ "$DRY_RUN" == false ]]; then
    while IFS= read -r filepath; do
        [[ -z "$filepath" ]] && continue
        [[ -n "${TRACKED_MAP[$filepath]:-}" ]] && continue
        matches_pattern_list "$filepath" "${SONARR_PROTECTED_PATTERNS[@]}" && continue

        FILE_MTIME=$(stat -c %Y "$filepath" 2>/dev/null || echo 0)
        FILE_AGE=$(( NOW - FILE_MTIME ))

        if has_extension "$filepath" "${SONARR_EXTENSIONS[@]}"; then
            [[ "$FILE_AGE" -lt "$AGE_SECONDS" ]] && \
                [[ "$SKIP_AGE_CHECK" != true ]] && continue
        fi

        rm -f "$filepath" 2>/dev/null || error "Failed to delete: $filepath"

    done < <(
        for host_path in "${SCAN_ROOTS[@]}"; do
            [[ -d "$host_path" ]] && find "$host_path" -type f 2>/dev/null
        done | sort -u
    )

    info "Cleaning up empty folders..."
    for host_path in "${SCAN_ROOTS[@]}"; do
        [[ -d "$host_path" ]] && \
            find "$host_path" -mindepth 1 -type d -empty -delete 2>/dev/null
    done
    info "Empty folders removed"
fi

END=$(date +%s)

ORPHAN_HUMAN=$(format_bytes "$ORPHAN_BYTES")
JUNK_HUMAN=$(format_bytes "$JUNK_BYTES")

# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo ""
echo "━━━━━ $ICON_SUMMARY SONARR CLEANUP SUMMARY ━━━━━"
echo "$ICON_HOST    Identity:        $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_SYNC    Tracked:         $TRACKED_COUNT files ($SERIES_COUNT series)"
echo "$ICON_SHIELD  Protected:       $PROTECTED_COUNT files (artwork, subtitles, metadata)"
echo "$ICON_TRASH   Orphans:         $ORPHAN_COUNT files ($ORPHAN_HUMAN)"
echo "$ICON_TRASH   Junk:            $JUNK_COUNT files ($JUNK_HUMAN)"
echo "$ICON_SKIP    Recent skipped:  $RECENT_COUNT files (under ${SONARR_ORPHAN_AGE} days)"
echo "$ICON_TIME    Duration:        $(format_duration $(( END - START )))"
echo ""

if [[ "$DRY_RUN" == true ]]; then
    warn "DRY RUN — no files deleted"
elif [[ "$TOTAL_REMOVED" -eq 0 ]]; then
    echo "$ICON_DONE Clean — nothing to remove"
else
    warn "$ICON_DONE Removed $TOTAL_REMOVED files (orphans: $ORPHAN_HUMAN junk: $JUNK_HUMAN)"
    notify "Sonarr cleanup on $(hostname) — removed $TOTAL_REMOVED files (orphans: $ORPHAN_HUMAN junk: $JUNK_HUMAN)" \
        "Sonarr Cleanup" "warning"
    # Notify Emby to clean missing files — removes ghost entries immediately
    notify_emby_scan
fi
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"

# Write stats for sunday_morning_coffee_report.sh
if [[ "$DRY_RUN" == false ]] && [[ -n "${ARR_CLEANUP_STATS:-}" ]]; then
    echo "$(date '+%Y-%m-%d')|sonarr|${ORPHAN_COUNT}|${ORPHAN_BYTES}|${JUNK_COUNT}|${JUNK_BYTES}|${RECENT_COUNT}|${TRACKED_COUNT}" \
        >> "$ARR_CLEANUP_STATS" 2>/dev/null || true
fi

exit 0