#!/bin/bash
# ==============================================================================================
# ================================= Media Cleaner ==============================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# Remove scene debris, tool artifacts, and unsafe files from media shares
# before the orphan scan — so arr cleanup only encounters actual media files.
# Runs second in the daily window, after permissions and before arr cleanup.
# Two profiles — anime and media — each with their own folder list and patterns.
#
# ==============================================================================================
# OPERATIONAL MODEL
# ==============================================================================================
#
# Profiles:
#   anime — cleans ANIME_CLEAN_FOLDERS using ANIME_FILE_PATTERNS
#   media — cleans MEDIA_CLEAN_FOLDERS using MEDIA_FILE_PATTERNS (adds *.iso *.lrc)
#
# Scene debris — left by scene releases and download clients:
#   *.sfv *.md5 *.sha1        — checksums — useless post-download
#   *.nzb *.torrent           — download files left by clients
#   *.url *.lnk *.info *.diz  — scene metadata
#   *.sample* *.proof*        — scene samples — never needed in library
#   *sync-conflict*           — Syncthing conflict copies
#   *.rar *.zip *.7z *.ace    — archives — source not needed after extraction
#   *.r00-*.r09 *.srr         — multi-part rar segments and repair files
#   *.001 *.002 *.003         — split archive parts
#   *.gz *.tar *.bz2          — linux archives
#
# Tool artifacts — incomplete or stale files from download clients:
#   *.!ut *.!qB               — uTorrent / qBittorrent incomplete markers
#   *.crdownload *.opdownload — Chrome / Opera incomplete downloads
#   *.part                    — partial download files
#
# Unsafe files — executables that should never appear in a media folder:
#   *.exe *.scr *.com         — Windows executables
#   *.bat *.cmd *.vbs *.ps1   — Windows scripts
#   *.msi *.dll *.sys         — Windows system files
#   *.sh                      — shell scripts in media folders = suspicious
#
# Media profile also removes: *.iso *.lrc
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
#   acquire_lock "wait"  — wait if previous run still active
#   detect_hosts()       — correct folder lists per host via MY_ID aliases
#   Empty array guards   — warns and exits cleanly if no folders or patterns configured
#   Folder existence     — skips missing folders with warning, continues others
#   platform_require_cmd  — notify script validated before use
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# host*.conf
#
#   HOST*_ANIME_CLEAN_FOLDERS — folders cleaned by the anime profile on this host
#   HOST*_MEDIA_CLEAN_FOLDERS — folders cleaned by the media profile on this host
#   Aliased by detect_hosts() — script uses ANIME_CLEAN_FOLDERS / MEDIA_CLEAN_FOLDERS
#
# master.conf
#
#   ANIME_FILE_PATTERNS  — file patterns removed by the anime profile
#   MEDIA_FILE_PATTERNS  — file patterns removed by the media profile
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
#   media_cleaner.sh anime              — clean anime shares
#   media_cleaner.sh media              — clean media shares
#   media_cleaner.sh anime --dry-run    — preview anime clean, no deletions
#   media_cleaner.sh media --dry-run    — preview media clean, no deletions
#   media_cleaner.sh anime --log        — verbose output
#   media_cleaner.sh anime --status     — show config and exit
#
# ==============================================================================================

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

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

# ── Separate profile argument from flags ──────────────────────────────────────────────────────
# Profile (anime|media) is a positional arg — separate before parse_args sees flags
PROFILE=""
RAW_ARGS=()

for ARG in "$@"; do
    case "$ARG" in
        anime|media) PROFILE="$ARG" ;;
        *)           RAW_ARGS+=("$ARG") ;;
    esac
done

parse_args "${RAW_ARGS[@]}"

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

if [[ -z "$PROFILE" ]]; then
    error "No profile specified"
    error "Usage: media_cleaner.sh <anime|media> [--dry-run] [--log] [--status]"
    exit 1
fi

acquire_lock "wait"

# detect_hosts() sets MY_ID and aliases HOST*_ANIME/MEDIA_CLEAN_FOLDERS
detect_hosts

platform_require_cmd \
    "/usr/local/emhttp/plugins/dynamix/scripts/notify" \
    "" "" \
    "unRAID notify script" || warn "unRAID notify script not found — native notifications disabled"

# Resolve profile folders and patterns
case "$PROFILE" in
    anime)
        CLEAN_FOLDERS=("${ANIME_CLEAN_FOLDERS[@]}")
        FILE_PATTERNS=("${ANIME_FILE_PATTERNS[@]}")
        ;;
    media)
        CLEAN_FOLDERS=("${MEDIA_CLEAN_FOLDERS[@]}")
        FILE_PATTERNS=("${MEDIA_FILE_PATTERNS[@]}")
        ;;
    *)
        error "Unknown profile: $PROFILE — must be anime or media"
        exit 1
        ;;
esac

# Empty array guards
if [[ ${#CLEAN_FOLDERS[@]} -eq 0 ]]; then
    warn "No folders configured for profile '$PROFILE' on $MY_ID"
    warn "Check HOST*_${PROFILE^^}_CLEAN_FOLDERS in host*.conf"
    exit 0
fi

if [[ ${#FILE_PATTERNS[@]} -eq 0 ]]; then
    warn "No file patterns configured for profile '$PROFILE'"
    warn "Check ${PROFILE^^}_FILE_PATTERNS in master.conf"
    exit 0
fi

log "Profile:  $PROFILE"
log "Folders:  ${#CLEAN_FOLDERS[@]}"
log "Patterns: ${#FILE_PATTERNS[@]}"

# ==============================================================================================
# ━━━ Status ━━━
# ==============================================================================================
if [[ "$SHOW_STATUS" == true ]]; then
    echo ""
    echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
    echo "$ICON_HOST    Identity: $MY_ID ($LOCAL_SERVER_NAME)"
    echo "$ICON_GEAR    Profile:  $PROFILE"
    echo "$ICON_CLEAN   Folders:"
    for f in "${CLEAN_FOLDERS[@]}"; do
        echo "              $f"
    done
    echo "$ICON_TRASH   Patterns: ${FILE_PATTERNS[*]}"
    echo "$ICON_GEAR    Dry Run:  $DRY_RUN"
    echo "━━━━━━━━━━━━━━━━━━━━━━━"
    exit 0
fi

[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no files will be deleted"

# ==============================================================================================
# ━━━ Media Cleaner ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_CLEAN Media Cleaner — $PROFILE — $MY_ID ━━━"
echo ""

START=$(date +%s)
TOTAL_REMOVED=0
FAILED=()
SKIPPED=()

for FOLDER in "${CLEAN_FOLDERS[@]}"; do
    FOLDER_NAME=$(basename "$FOLDER")
    echo "━━━ $ICON_CLEAN $FOLDER_NAME ━━━"

    if [[ ! -d "$FOLDER" ]]; then
        warn "$FOLDER_NAME not found — skipping"
        SKIPPED+=("$FOLDER_NAME")
        echo ""
        continue
    fi

    # Build find command dynamically from FILE_PATTERNS array
    CMD=(find "$FOLDER" -type f \()
    for (( i = 0; i < ${#FILE_PATTERNS[@]}; i++ )); do
        CMD+=(-iname "${FILE_PATTERNS[i]}")
        if [[ $i -lt $(( ${#FILE_PATTERNS[@]} - 1 )) ]]; then
            CMD+=(-o)
        fi
    done
    CMD+=(\))

    # Count matching files before acting
    FILE_COUNT=$("${CMD[@]}" 2>/dev/null | wc -l)

    if [[ "$FILE_COUNT" -eq 0 ]]; then
        log "$FOLDER_NAME — clean ✅"
        echo ""
        continue
    fi

    warn "$ICON_TRASH $FILE_COUNT file(s) to remove from $FOLDER_NAME"

    if [[ "$DRY_RUN" == true ]]; then
        warn "DRY RUN — files that would be deleted:"
        "${CMD[@]}" 2>/dev/null | while IFS= read -r f; do
            echo "    $ICON_TRASH $f"
        done
    else
        CLEAN_CMD=("${CMD[@]}" -exec rm -f {} +)
        if "${CLEAN_CMD[@]}" 2>/dev/null; then
            log "$FOLDER_NAME — $FILE_COUNT file(s) removed"
            TOTAL_REMOVED=$(( TOTAL_REMOVED + FILE_COUNT ))
        else
            error "$FOLDER_NAME — cleanup failed"
            FAILED+=("$FOLDER_NAME")
        fi
    fi

    echo ""
done

END=$(date +%s)

# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo "━━━━━ $ICON_SUMMARY MEDIA CLEANER SUMMARY ━━━━━"
echo "$ICON_HOST    Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_GEAR    Profile:  $PROFILE"
echo "$ICON_TIME    Duration: $(format_duration $(( END - START )))"
[[ ${#SKIPPED[@]} -gt 0 ]] && warn "Skipped:  ${SKIPPED[*]} (folders not found)"
[[ ${#FAILED[@]} -gt 0 ]]  && echo "$ICON_ERROR   Failed:   ${FAILED[*]}"

if [[ "$DRY_RUN" == true ]]; then
    warn "DRY RUN — no files deleted"
elif [[ ${#FAILED[@]} -gt 0 ]]; then
    echo "$ICON_ERROR   Status: SOME FOLDERS FAILED"
    notify "Media cleaner ($PROFILE) failed on $(hostname) — ${FAILED[*]}" \
        "Media Cleaner" "warning"
elif [[ "$TOTAL_REMOVED" -eq 0 ]]; then
    echo "$ICON_DONE Status: clean — nothing to remove"
else
    warn "$ICON_TRASH Removed: $TOTAL_REMOVED file(s)"
    notify "Media cleaner ($PROFILE) on $(hostname) — $TOTAL_REMOVED file(s) removed" \
        "Media Cleaner" "warning"
fi
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"

[[ ${#FAILED[@]} -gt 0 ]] && exit 1
exit 0