#!/usr/bin/env bash
set -Eeuo pipefail

###############################################################################
# dockerbackup_prune.sh
#
# A) Create a dated .zst backup of /dockerbackups (tar stream | zstd, output .zst)
#    - Clean single-line progress with percent and current dir/file (requires pv)
#    - Fallback: single-line [N/TOTAL] without percent if pv is unavailable
# B) Upload via rclone
# C) Prune *.zst under PRUNE_ROOT subfolders, keeping newest N per subfolder
# D) Delete the local .zst (only with --apply)
#
# Restore:
#   zstd -d -c /path/backup.zst | tar -x -C /restore/target
###############################################################################

# --------------------------- Defaults (can be overridden) --------------------
SOURCE_DIR="/mybackups"                             # what to archive
PRUNE_ROOT="/mybackups"                             # where to prune .zst
PRUNE_PATTERN="*.zst"                               # files to prune
KEEP_COUNT=5                                        # keep newest N per subfolder

RCLONE_REMOTE="gdrive:location/sublocation"         # rclone destination
OUT_DIR="/tmp"                                      # where to write the .zst
BACKUP_PREFIX="panda-dockerbackup"                  # backup name prefix

# Optional zstd tuning, e.g. "-19 -T0" for max level, multithread
ZSTD_EXTRA_OPTS=""

# --------------------------- Load .env (same dir as script) -----------------
# Order of precedence:
#   defaults < .env (same dir) < CLI flags
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)"
ENV_FILE="${DOCKERBACKUP_ENV:-$SCRIPT_DIR/.env}"
if [[ -f "$ENV_FILE" ]]; then
  # Warn if perms are too open; still load to keep it convenient
  perms="$(stat -c '%a' "$ENV_FILE" 2>/dev/null || stat -f '%Lp' "$ENV_FILE" 2>/dev/null || echo '')"
  if [[ -n "$perms" && ! "$perms" =~ ^(600|400)$ ]]; then
    echo "$(date '+%F %T') [WARN] $ENV_FILE permissions are $perms; recommend 600." >&2
  fi
  set -a
  # shellcheck disable=SC1090
  . "$ENV_FILE"
  set +a
fi

# --------------------------- CLI flags --------------------------------------
APPLY=0
QUIET=0
DRYRUN=0

usage() {
  cat <<EOF
Usage: $0 [--apply] [--quiet] [--dry-run] [--keep N] [--root PATH] [--source PATH] [--outdir PATH] [--remote PATH]

Default: creates and uploads backup, shows what WOULD be deleted (no deletes).

Flags:
  --apply        Actually delete pruned files and the local .zst
  --quiet        Minimal console output (no live progress)
  --dry-run      Simulate everything (no backup, no upload, no deletes)
  --keep N       Keep newest N .zst files per subfolder (default ${KEEP_COUNT})
  --root PATH    Root folder to prune (default ${PRUNE_ROOT})
  --source PATH  Folder to archive (default ${SOURCE_DIR})
  --outdir PATH  Where to write the .zst (default ${OUT_DIR})
  --remote PATH  rclone destination (default ${RCLONE_REMOTE})

Environment file:
  A .env file in the same directory as this script is loaded automatically.
  You can override its path by setting DOCKERBACKUP_ENV=/path/to/.env
EOF
}

while [[ $# -gt 0 ]]; do
  case "$1" in
    --apply) APPLY=1 ;;
    --quiet) QUIET=1 ;;
    --dry-run) DRYRUN=1 ;;
    --keep) KEEP_COUNT="${2:?}"; shift ;;
    --root) PRUNE_ROOT="${2:?}"; shift ;;
    --source) SOURCE_DIR="${2:?}"; shift ;;
    --outdir) OUT_DIR="${2:?}"; shift ;;
    --remote) RCLONE_REMOTE="${2:?}"; shift ;;
    -h|--help) usage; exit 0 ;;
    *) echo "Unknown option: $1" >&2; usage; exit 2 ;;
  esac
  shift
done

# --------------------------- Logging helpers --------------------------------
ts() { date '+%F %T'; }
log() { [[ $QUIET -eq 0 ]] && echo "$(ts) [$1] $2"; }
log_err() { echo "$(ts) [ERROR] $1" >&2; }
run() { if [[ $DRYRUN -eq 1 ]]; then log "DRY" "$*"; else "$@"; fi; }

# Truncate to terminal width and erase tail so old text is cleared
truncate_and_print() {
  local s="$1" cols
  if [[ -t 2 ]]; then
    cols=$(tput cols 2>/dev/null || echo 120)
  else
    cols=120
  fi
  (( cols<20 )) && cols=120
  if (( ${#s} > cols-1 )); then
    s="${s:0:cols-1}"
  fi
  printf '\r%s\033[K' "$s" >&2
}

cleanup_tmp=""
pipe_pid=""
pipe_pgid=""
pct_fd_open=0
path_fd_open=0
status_line_shown=0

cleanup() {
  local why="${1:-EXIT}"
  # Kill the whole pipeline (tar|pv|zstd)
  if [[ -n "$pipe_pid" ]]; then
    if command -v ps >/dev/null 2>&1; then
      pipe_pgid=$(ps -o pgid= "$pipe_pid" 2>/dev/null | tr -d ' ' || true)
    fi
    if [[ -n "$pipe_pgid" ]]; then
      kill -TERM "-$pipe_pgid" 2>/dev/null || true
      sleep 0.2
      kill -KILL "-$pipe_pgid" 2>/dev/null || true
    else
      kill -TERM "$pipe_pid" 2>/dev/null || true
      sleep 0.2
      kill -KILL "$pipe_pid" 2>/dev/null || true
    fi
    wait "$pipe_pid" 2>/dev/null || true
  fi
  # Close FDs
  if (( pct_fd_open == 1 )); then exec 4>&- 4<&-; pct_fd_open=0; fi
  if (( path_fd_open == 1 )); then exec 3>&- 3<&-; path_fd_open=0; fi
  # Remove fifos/dir
  if [[ -n "$cleanup_tmp" ]]; then
    rm -f "$cleanup_tmp/pct" "$cleanup_tmp/path" 2>/dev/null || true
    rmdir "$cleanup_tmp" 2>/dev/null || true
  fi
  # End the progress line cleanly
  if (( status_line_shown == 1 )) && [[ $QUIET -eq 0 ]]; then
    printf '\n' >&2
  fi
  # Exit with 130 on INT/TERM
  case "$why" in
    INT|TERM) exit 130 ;;
  esac
}

trap 'log_err "Command failed: $BASH_COMMAND"; cleanup ERR; exit 1' ERR
trap 'cleanup INT' INT
trap 'cleanup TERM' TERM
trap 'cleanup EXIT' EXIT

# --------------------------- Preconditions ----------------------------------
[[ -d "$SOURCE_DIR" ]] || { log_err "Source dir not found: $SOURCE_DIR"; exit 1; }
[[ -d "$PRUNE_ROOT" ]] || { log_err "Prune root not found: $PRUNE_ROOT"; exit 1; }
command -v tar >/dev/null 2>&1 || { log_err "tar not found"; exit 1; }
command -v zstd >/dev/null 2>&1 || { log_err "zstd not found"; exit 1; }
command -v rclone >/dev/null 2>&1 || { log_err "rclone not found"; exit 1; }
command -v find >/dev/null 2>&1 || { log_err "find not found"; exit 1; }

# Timestamp in name: YYYY-MM-DD_HH-MM (system timezone or override externally)
STAMP="${STAMP_OVERRIDE:-$(date +%F_%H-%M)}"
BACKUP_NAME="${BACKUP_PREFIX}-${STAMP}.zst"
BACKUP_PATH="${OUT_DIR%/}/${BACKUP_NAME}"

RCLONE_FLAGS=()
[[ $QUIET -eq 1 ]] && RCLONE_FLAGS+=("-q") || RCLONE_FLAGS+=("--progress")

# Silence zstd "Read: ... ==> 100%"
ZSTD_FLAGS=("-q")
[[ -n "$ZSTD_EXTRA_OPTS" ]] && ZSTD_FLAGS+=($ZSTD_EXTRA_OPTS)

log "INFO" "Mode: $( [[ $DRYRUN -eq 1 ]] && echo 'DRY-RUN ALL' || ([[ $APPLY -eq 1 ]] && echo 'APPLY DELETES' || echo 'NO DELETES') )"
log "INFO" "Creating archive: $BACKUP_PATH (.zst)"
log "INFO" "Keeping newest $KEEP_COUNT file(s) per subfolder matching: $PRUNE_PATTERN"
log "INFO" "Source: $SOURCE_DIR"
log "INFO" "Remote: $RCLONE_REMOTE"
log "INFO" "Prune root (root itself will be skipped): $PRUNE_ROOT"

# --------------------------- Step A: create .zst with one-liner --------------
log "STEP" "A) Creating archive"

if [[ $DRYRUN -eq 1 ]]; then
  log "DRY" "tar -C \"$SOURCE_DIR\" -cvf - . | pv -n -s \$(du -sb \"$SOURCE_DIR\"|cut -f1) 2>pct.fifo | zstd ${ZSTD_FLAGS[*]} -o \"$BACKUP_PATH\""
else
  mkdir -p "$OUT_DIR"

  export LC_ALL=C
  TOTAL_FILES=$(find "$SOURCE_DIR" -type f | wc -l | awk '{print $1}')
  TOTAL_BYTES=$(du -sb "$SOURCE_DIR" | cut -f1)

  tmpdir="$(mktemp -d)"; cleanup_tmp="$tmpdir"
  path_fifo="$tmpdir/path"; pct_fifo="$tmpdir/pct"
  mkfifo "$path_fifo"
  have_pv=0
  if command -v pv >/dev/null 2>&1 && [[ $QUIET -eq 0 ]] && [[ -t 2 ]]; then
    mkfifo "$pct_fifo"; have_pv=1
  fi

  # Open FIFOs RDWR so writers/readers never block
  exec 3<> "$path_fifo"; path_fd_open=1
  if (( have_pv == 1 )); then exec 4<> "$pct_fifo"; pct_fd_open=1; fi

  # Run pipeline in background; send tar -v names into the path FIFO
  if (( have_pv == 1 )); then
    (
      set -o pipefail
      tar -C "$SOURCE_DIR" -cvf - . \
        2> >(sed -u 's#^\./##' > "$path_fifo" || true) \
      | pv -n -s "$TOTAL_BYTES" 2> "$pct_fifo" \
      | zstd "${ZSTD_FLAGS[@]}" -o "$BACKUP_PATH"
    ) &
  else
    (
      set -o pipefail
      tar -C "$SOURCE_DIR" -cvf - . \
        2> >(sed -u 's#^\./##' > "$path_fifo" || true) \
      | zstd "${ZSTD_FLAGS[@]}" -o "$BACKUP_PATH"
    ) &
  fi
  pipe_pid=$!

  # Status loop: single clean line on stderr
  files_seen=0
  last_path=""
  last_pct="0.0"
  status_line_shown=0
  last_print_time=0

  while kill -0 "$pipe_pid" 2>/dev/null; do
    # read percent from pv (if any)
    if (( have_pv == 1 )); then
      if IFS= read -r -t 0.03 pct_line <&4; then last_pct="$pct_line"; fi
    fi
    # read latest path from tar
    if IFS= read -r -t 0.03 path_line <&3; then
      last_path="$path_line"
      [[ -n "$last_path" ]] && (( files_seen++ )) || true
    fi

    # Split into dir/file for display (already relative)
    display_rel="$last_path"
    dir_part="$(dirname -- "$display_rel" 2>/dev/null || echo .)"
    base_part="$(basename -- "$display_rel" 2>/dev/null || echo .)"
    [[ "$dir_part" == "." ]] && dir_part="."

    # Refresh line and erase tail (\033[K)
    if [[ $QUIET -eq 0 ]]; then
      now_ns=$(date +%s%N)
      if (( now_ns - last_print_time > 50000000 )); then
        if (( have_pv == 1 )); then
          line="[$(printf '%.1f' "${last_pct:-0}")%] archiving: ${dir_part}/ ${base_part}"
        else
          line="[${files_seen}/${TOTAL_FILES}] archiving: ${dir_part}/ ${base_part}"
        fi
        truncate_and_print "$line"
        status_line_shown=1
        last_print_time=$now_ns
      fi
    fi
  done

  # Drain, finish, cleanup
  while IFS= read -r -t 0.03 path_line <&3; do
    last_path="$path_line"; (( files_seen++ )) || true
    [[ $QUIET -eq 0 ]] && truncate_and_print "[${files_seen}/${TOTAL_FILES}] archiving: $(dirname -- "$last_path")/ $(basename -- "$last_path")"
    status_line_shown=1
  done || true

  wait "$pipe_pid"
  if [[ $QUIET -eq 0 ]]; then
    printf '\n' >&2
    status_line_shown=0
  fi

  # Close and clean up
  exec 3>&- 3<&-; path_fd_open=0
  if (( have_pv == 1 )); then exec 4>&- 4<&-; pct_fd_open=0; fi
  rm -f "$path_fifo" "$pct_fifo" 2>/dev/null || true
  rmdir "$tmpdir" 2>/dev/null || true
  cleanup_tmp=""
fi
log "OK" "Archive step completed"

# --------------------------- Step B: rclone copy -----------------------------
log "STEP" "B) rclone copy to remote"
if [[ $DRYRUN -eq 1 ]]; then
  log "DRY" "rclone copy \"$BACKUP_PATH\" \"$RCLONE_REMOTE\" ${RCLONE_FLAGS[*]}"
else
  run rclone copy "$BACKUP_PATH" "$RCLONE_REMOTE" "${RCLONE_FLAGS[@]}"
fi
log "OK" "Upload step completed"

# --------------------------- Step C: prune .zst ------------------------------
log "STEP" "C) Pruning $PRUNE_PATTERN under $PRUNE_ROOT (keep $KEEP_COUNT)"
export LC_ALL=C
prune_ok=1

while IFS= read -r -d '' dir; do
  mapfile -d '' -t files < <(
    find "$dir" -maxdepth 1 -type f -name "$PRUNE_PATTERN" -printf '%T@ %p\0' |
      sort -z -n |
      cut -z -d' ' -f2-
  )
  count=${#files[@]}
  if (( count == 0 )); then
    log "SKIP" "No matches in: $dir"
    continue
  fi

  keep_from=$(( count - KEEP_COUNT ))
  (( keep_from < 0 )) && keep_from=0

  if (( count <= KEEP_COUNT )); then
    log "KEEP" "At or below limit in: $dir (count=$count)"
    continue
  fi

  keep_list=("${files[@]:keep_from:KEEP_COUNT}")
  del_list=("${files[@]:0:keep_from}")

  for k in "${keep_list[@]}"; do
    log "KEEP" "Keep: $k"
  done
  for f in "${del_list[@]}"; do
    if [[ $DRYRUN -eq 1 || $APPLY -eq 0 ]]; then
      log "WOULD" "Remove: $f"
    else
      if rm -f -- "$f"; then
        log "DELETE" "Removed: $f"
      else
        log_err "Failed to remove: $f"; prune_ok=0
      fi
    fi
  done
done < <(find "$PRUNE_ROOT" -mindepth 1 -type d -print0)

if [[ $prune_ok -ne 1 ]]; then
  log_err "Prune step encountered errors; aborting final delete"
  exit 1
fi
log "OK" "Prune step completed"

# --------------------------- Step D: remove local .zst -----------------------
log "STEP" "D) Removing local backup"
if [[ $DRYRUN -eq 1 || $APPLY -eq 0 ]]; then
  log "WOULD" "Remove local backup: $BACKUP_PATH"
else
  if rm -f -- "$BACKUP_PATH"; then
    log "DELETE" "Removed local backup: $BACKUP_PATH"
  else
    log_err "Failed to remove local backup: $BACKUP_PATH"
    exit 1
  fi
fi

log "DONE" "All steps completed successfully"