#!/bin/bash
# ${PIPELINE_DIR:-/app/pipeline}/lib/tag-guard.sh
#
# Shared helper sourced by run-playlist.sh and import-track.sh.
# Moves audio files with missing ARTIST or TITLE tags into a quarantine dir,
# so they never reach beets and rot the library as "[Unknown Album]".
#
# Usage:  quarantine_untagged <scan_dir> <quarantine_dir> <log_file>
# Returns: number of files moved (via stdout)

# Separator pattern matching Navidrome's artist split list in navidrome.toml.
# Used by set_albumartist_fallback to extract the primary artist from a multi-
# artist string. Keep these two lists in sync.
#
# Only unambiguous separators here. ", " and " & " are NOT included because they
# appear inside real band names ("Tyler, The Creator", "Simon & Garfunkel",
# "piri & tommy"). For collab strings using those separators, ALBUMARTIST falls
# back to the full string — Navidrome will show one combined artist for the album,
# which is the lesser of two evils vs. corrupting real band names.
_PRIMARY_ARTIST_SEP_PATTERN=' / | feat\. | feat | ft\. | ft |; '

# For each audio file under $scan_dir that has no ALBUMARTIST tag, set
# ALBUMARTIST to the primary artist (everything before the first separator
# in the ARTIST tag). Prevents Navidrome from coining ghost album-artists
# like "Fred Again, The Blessed Madonna" when a track is a collab.
#
# Usage:  set_albumartist_fallback <scan_dir> <log_file>
# Returns: number of files updated (via stdout)
set_albumartist_fallback() {
  local scan_dir="$1"
  local logfile="$2"
  local count=0

  while IFS= read -r -d '' file; do
    case "${file##*.}" in
      flac|FLAC)
        local cur_aa artist primary
        cur_aa=$(metaflac --show-tag=ALBUMARTIST "$file" 2>/dev/null | sed -n 's/^[^=]*=//p' | head -1)
        [[ -n "$cur_aa" ]] && continue
        artist=$(metaflac --show-tag=ARTIST "$file" 2>/dev/null | sed -n 's/^[^=]*=//p' | head -1)
        [[ -z "$artist" ]] && continue
        primary=$(echo "$artist" | sed -E "s#(${_PRIMARY_ARTIST_SEP_PATTERN}).*##")
        metaflac --set-tag="ALBUMARTIST=${primary}" "$file" 2>>"$logfile"
        count=$((count + 1))
        ;;
      mp3|MP3)
        local cur_aa artist primary
        cur_aa=$(id3v2 -l "$file" 2>/dev/null | sed -n 's/^TPE2[^:]*: //p' | head -1)
        [[ -n "$cur_aa" ]] && continue
        artist=$(id3v2 -l "$file" 2>/dev/null | sed -n 's/^TPE1[^:]*: //p' | head -1)
        [[ -z "$artist" ]] && continue
        primary=$(echo "$artist" | sed -E "s#(${_PRIMARY_ARTIST_SEP_PATTERN}).*##")
        id3v2 --TPE2 "$primary" "$file" 2>>"$logfile"
        count=$((count + 1))
        ;;
    esac
  done < <(find "$scan_dir" -type f \( -iname "*.flac" -o -iname "*.mp3" \) -print0 2>/dev/null)

  echo "$count"
}

quarantine_untagged() {
  local scan_dir="$1"
  local quarantine_dir="$2"
  local logfile="$3"
  local moved=0

  mkdir -p "$quarantine_dir"

  _has_flac_tags() {
    local artist title
    artist=$(metaflac --show-tag=ARTIST "$1" 2>/dev/null | sed -n 's/^[^=]*=//p' | head -1)
    title=$(metaflac  --show-tag=TITLE  "$1" 2>/dev/null | sed -n 's/^[^=]*=//p'  | head -1)
    [[ -n "$artist" && -n "$title" ]]
  }

  _has_mp3_tags() {
    local artist title
    artist=$(id3v2 -l "$1" 2>/dev/null | sed -n 's/^TPE1[^:]*: //p' | head -1)
    title=$(id3v2  -l "$1" 2>/dev/null | sed -n 's/^TIT2[^:]*: //p' | head -1)
    [[ -n "$artist" && -n "$title" ]]
  }

  while IFS= read -r -d '' file; do
    local ok=1
    case "${file##*.}" in
      flac|FLAC) _has_flac_tags "$file" || ok=0 ;;
      mp3|MP3)   _has_mp3_tags  "$file" || ok=0 ;;
      *)         ok=0 ;;   # unknown format — beets can't handle it anyway
    esac
    if [[ $ok -eq 0 ]]; then
      echo "[$(date -Iseconds)] QUARANTINE: missing artist/title — $(basename "$file")" >> "$logfile"
      mv -n "$file" "$quarantine_dir/" 2>>"$logfile"
      moved=$((moved + 1))
    fi
  done < <(find "$scan_dir" -type f \( -iname "*.flac" -o -iname "*.mp3" -o -iname "*.m4a" \) -print0 2>/dev/null)

  echo "$moved"
}