#!/bin/bash
# Normalize every finished original so editors always get the same kind of file:
#   MP4 · H.264 8-bit 4:2:0 · constant frame rate · AAC audio · index up front · ≤2560x1440 · ≤60 fps
# - compliant files: untouched
# - fragmented/unindexed MP4 (MediaMTX output) with good codecs: lossless remux, replaced in place
# - anything else (HEVC, 10-bit, VFR, MKV, >1440p, >60fps): full-res re-encode -> name.mp4,
#   raw source kept in a hidden .src/ subfolder next to it (Jellyfin/copyparty hide dot-dirs)
# - streams/<user>/<Title>/.live/<ts>.mp4 (MediaMTX writes here, hidden from Jellyfin/copyparty while live):
#   when finished -> the timecode overscan band (if the streamer had it on) is decoded and then CROPPED OFF in a
#   re-encode (libx264, frame timing preserved, audio copied) so the published file is the game image + audio +
#   a tmcd timecode track, nothing else; streams without the band are remuxed losslessly. Published as flat
#   MP4 streams/<user>/<Title>__<ts>.mp4 (one file per recording directly
#   in the streamer's folder: Jellyfin would merge several files inside one title folder into ONE episode
#   with "versions"), the .live source deleted, the empty title folder removed.
# - Syncthing folders (marker dir .stfolder in the folder root, receive-only): compliant files are left
#   alone (zero copies); a non-compliant file is converted to name.mp4 (name.h264.mp4 if the raw is
#   already .mp4), the raw's name is appended to .stlocal (an #include'd ignore list) so Syncthing
#   drops it without flagging or re-pulling, then the raw is deleted. One copy on the server.
# - failure: name.normalize-failed.log is written and the file is skipped until that log is deleted
# Idempotent; safe every few minutes.
set -uo pipefail

ROOT="${MEDIA_ROOT:-/srv/media}"
MINS_IDLE=3
# Gap filling for STREAMS: re-encode to constant frame rate (duplicating frames across dropped-frame holes) when
# the total missing time is >= this many ms. 0 = never (default; a 3 h re-encode is ~6 h of CPU on the E-2136).
# Set via systemd Environment=FILL_GAPS_MS=... ; viewers already see held frames either way.
FILL_GAPS_MS="${FILL_GAPS_MS:-0}"
# Band removal re-encodes every stream that carried the timecode band. The raw (with band) is deleted after a
# successful encode; KEEP_RAW_STREAMS=1 keeps it in the hidden .src/ instead (doubles disk per night).
KEEP_RAW_STREAMS="${KEEP_RAW_STREAMS:-0}"
# Encoder threads for every re-encode (clips and streams). 2 leaves the box responsive for Jellyfin/live viewers;
# conversions take longer. systemd Environment=ENCODE_THREADS=... to change.
ENCODE_THREADS="${ENCODE_THREADS:-2}"
MAX_W=2560; MAX_H=1440; MAX_FPS=60
exec 9>"${LOCK_FILE:-/run/lock/normalize-sweep.lock}"
flock -n 9 || exit 0

# logfmt (LOGGING.md): vglog <level> event=<verb> key=value ...   values with spaces must arrive pre-quoted
vglog() { local lvl="$1"; shift; printf 'ts=%s level=%s component=sweep %s\n' "$(date -Is)" "$lvl" "$*"; }
log() { vglog info "msg=\"$*\""; }
dur() { ffprobe -v error -show_entries format=duration -of csv=p=0 "$1" 2>/dev/null | cut -d. -f1; }

# --- probe: prints "verdict reason" where verdict ∈ ok|remux|encode|skip ----------------------
probe() {
  local f="$1" ext="${1##*.}"
  local json; json=$(ffprobe -v error -show_entries stream=codec_type,codec_name,pix_fmt,width,height,r_frame_rate,avg_frame_rate -of json "$f" 2>/dev/null) || { echo "skip unreadable"; return; }
  local vcodec pix w h rfr afr acodecs
  vcodec=$(jq -r '[.streams[]|select(.codec_type=="video")][0].codec_name // "none"' <<<"$json")
  pix=$(jq -r '[.streams[]|select(.codec_type=="video")][0].pix_fmt // ""' <<<"$json")
  w=$(jq -r '[.streams[]|select(.codec_type=="video")][0].width // 0' <<<"$json")
  h=$(jq -r '[.streams[]|select(.codec_type=="video")][0].height // 0' <<<"$json")
  rfr=$(jq -r '[.streams[]|select(.codec_type=="video")][0].r_frame_rate // "0/1"' <<<"$json")
  afr=$(jq -r '[.streams[]|select(.codec_type=="video")][0].avg_frame_rate // "0/1"' <<<"$json")
  acodecs=$(jq -r '[.streams[]|select(.codec_type=="audio")|.codec_name]|unique|join(",")' <<<"$json")
  [[ $vcodec == none ]] && { echo "skip no-video"; return; }
  local fps; fps=$(awk -F/ '{ if ($2>0) printf "%.3f", $1/$2; else print 0 }' <<<"$afr")
  local reasons=()
  [[ $vcodec == h264 ]]            || reasons+=("codec=$vcodec")
  [[ $pix == yuv420p ]]            || reasons+=("pix=$pix")
  (( w <= MAX_W && h <= MAX_H ))   || reasons+=("size=${w}x${h}")
  awk "BEGIN{exit !($fps > $MAX_FPS + 0.01)}" && reasons+=("fps=$fps")
  [[ -z $acodecs || $acodecs == aac ]] || reasons+=("audio=$acodecs")
  [[ ${ext,,} == mp4 ]]            || reasons+=("container=$ext")
  if (( ${#reasons[@]} )); then echo "encode ${reasons[*]}"; return; fi
  # codecs fine. Fragmented MP4 (MediaMTX output) -> lossless remux. ffprobe's frame-rate figures are
  # meaningless on fragmented files, so the VFR check only runs on flat files (i.e. after the remux).
  local head; head=$(head -c 2097152 "$f" | grep -aob -m3 -E 'moov|mdat|moof' | tr '\n' ' ')
  if grep -q moof <<<"$head"; then echo "remux fragmented"; return; fi
  # real VFR test: do the gaps between the first ~400 frames vary? (dts is monotonic even with B-frames)
  # portable awk (Debian's mawk has no asort): deltas -> sort -n -> median + spread
  local vfr; vfr=$(ffprobe -v error -select_streams v:0 -show_entries packet=dts_time -of csv=p=0 -read_intervals '%+#400' "$f" 2>/dev/null |
    awk 'NF && $1!="N/A" { if (p!="") print $1-p; p=$1 }' | sort -n |
    awk '{ d[n++]=$1 }
         END { if (n<20) { print "cfr"; exit }
               med=d[int(n/2)]; if (med<=0) { print "cfr"; exit }
               bad=0; for(i=0;i<n;i++){ x=d[i]-med; if(x<0)x=-x; if (x > med*0.25) bad++ }
               print (bad > n*0.02) ? "vfr" : "cfr" }')
  # streams: gaps from dropped frames are legitimate and re-encoding a 3 h file is hours of CPU — never VFR-encode
  # them (the timecode sidecar lists the gaps instead). Clips (short, often genuinely VFR) still get CFR.
  if [[ $vfr == vfr && $f != "$ROOT/streams/"* ]]; then echo "encode vfr"; return; fi
  local moov mdat; moov=$(grep -o '[0-9]*:moov' <<<"$head" | cut -d: -f1 | head -1); mdat=$(grep -o '[0-9]*:mdat' <<<"$head" | cut -d: -f1 | head -1)
  if [[ -z $moov || ( -n $mdat && $mdat -lt $moov ) ]]; then echo "remux index-last"; return; fi
  echo "ok"
}

find "$ROOT/streams" "$ROOT/clips" -type f \
     \( -iname '*.mp4' -o -iname '*.mkv' -o -iname '*.mov' -o -iname '*.ts' -o -iname '*.m4v' -o -iname '*.webm' \) \
     ! -path '*/.src/*' ! -path '*/.stfolder/*' ! -path '*/.stversions/*' ! -name '*.part' -mmin +"$MINS_IDLE" -print0 2>/dev/null |
while IFS= read -r -d '' src; do
  base="${src%.*}"; ext="${src##*.}"
  live=0; stream=""
  if [[ $(basename "$(dirname "$src")") == .live ]]; then
    live=1
    titledir="$(dirname "$(dirname "$src")")"                       # streams/<user>/<Title>
    stream="$(basename "$(dirname "$titledir")")/$(basename "$titledir")"   # user/Title, the log correlation key
    base="$(dirname "$titledir")/$(basename "$titledir")__$(basename "${src%.*}")"   # streams/<user>/<Title>__<ts>
  fi
  synced=0; stroot=""
  d="$(dirname "$src")"
  while [[ $d == "$ROOT"/* ]]; do                          # find the Syncthing folder root, if any
    if [[ -d "$d/.stfolder" ]]; then synced=1; stroot="$d"; break; fi
    d="$(dirname "$d")"
  done
  [[ -e "$base.normalize-failed.log" ]] && continue
  fuser -s "$src" 2>/dev/null && continue            # still being written
  [[ -e "$src" ]] || continue                          # dumped meanwhile

  read -r verdict reason <<<"$(probe "$src")"
  if (( live )); then
    [[ $verdict == skip ]] && continue
    [[ $verdict == ok ]] && verdict=remux          # must leave .live/ either way
    out="$base.mp4"; [[ -e "$out" ]] && { vglog info "event=skip reason=exists file=\"$out\" src=\"$src\""; continue; }
  else
    case "$verdict" in ok|skip) continue ;; esac
    out="$base.mp4"
  fi
  if (( synced )); then
    [[ $verdict == remux ]] && continue                    # synced + only an index issue: not worth touching
    [[ ${ext,,} == mp4 ]] && out="$base.h264.mp4"          # raw is already name.mp4: don't collide
    [[ -e "$out" ]] && continue
  fi
  tmp="$out.part"
  vglog info "event=verdict verdict=$verdict file=\"$src\" reason=\"$reason\" stream=\"$stream\""
  tcargs=(); tcjson=""; band=0; deband=0
  if (( live )); then
    # timecode: decode the overscan strip (server clock) or fall back to the server arrival time in the filename
    stem="$(basename "${src%.*}")"
    arrival_ms=$(python3 - "$stem" <<'PYEOF'
import re, sys
from datetime import datetime
from zoneinfo import ZoneInfo
m = re.search(r"(\d{4})-(\d{2})-(\d{2})_(\d{2})-(\d{2})-(\d{2})(?:-(\d{1,6}))?", sys.argv[1])
if not m: sys.exit(0)
y, mo, d, h, mi, s, us = m.groups()
us = int((us or "0").ljust(6, "0"))
t = datetime(int(y), int(mo), int(d), int(h), int(mi), int(s), us, tzinfo=ZoneInfo("America/New_York"))
print(int(t.timestamp() * 1000))
PYEOF
)
    eval "$(python3 /usr/local/bin/vgstrip.py plan "$src" "${arrival_ms:-}" 2>/dev/null || true)"
    if [[ -n ${TC_TIMECODE:-} ]]; then
      tcargs=(-timecode "$TC_TIMECODE" -metadata "creation_time=$TC_CREATION" -write_tmcd 1)
      tcjson="${TC_JSON:-}"
      vglog info "event=timecode file=\"$src\" stream=\"$stream\" source=$TC_SOURCE timecode=\"$TC_TIMECODE\""
    fi
    # the band has done its job once decoded: remove it from the picture (re-encode with a crop)
    if [[ ${TC_SOURCE:-} == strip && ${TC_BAND:-0} -gt 0 ]]; then
      band=$TC_BAND; deband=1; verdict=encode; reason="remove ${band}px timecode band"
      vglog info "event=deband file=\"$src\" stream=\"$stream\" band_rows=$band"
    fi
    # opt-in gap filling: switch this stream from remux to a CFR re-encode when the holes add up to enough
    if (( FILL_GAPS_MS > 0 )) && [[ $verdict == remux && -n $tcjson ]]; then
      missing=$(python3 -c 'import json,sys; d=json.loads(sys.argv[1]); print(d.get("gaps",{}).get("total_missing_ms",0))' "$tcjson" 2>/dev/null || echo 0)
      if (( missing >= FILL_GAPS_MS )); then
        verdict=encode; reason="fill-gaps ${missing}ms"; vglog info "event=fill_gaps file=\"$src\" stream=\"$stream\" missing_ms=$missing"
      fi
    fi
  fi
  if [[ $verdict == remux ]]; then
    nice -n 15 ionice -c 3 ffmpeg -nostdin -hide_banner -loglevel error -y -i "$src" \
      -map 0 -c copy "${tcargs[@]}" -movflags +faststart -f mp4 "$tmp"
  else
    # scale down into the cap (never up), keep aspect, even dimensions; cap fps; CFR; all audio -> AAC
    vf="scale='min(iw,$MAX_W)':'min(ih,$MAX_H)':force_original_aspect_ratio=decrease:force_divisible_by=2"
    (( deband )) && vf="crop=iw:ih-${band}:0:0,$vf"          # drop the band rows first (band is even, so sizes stay even)
    fpsargs=(); fpsnow=$(awk -F/ '{ if ($2>0) printf "%.3f", $1/$2; else print 0 }' <<<"$(ffprobe -v error -select_streams v:0 -show_entries stream=avg_frame_rate -of csv=p=0 "$src")")
    awk "BEGIN{exit !($fpsnow > $MAX_FPS + 0.01)}" && fpsargs=(-r "$MAX_FPS")
    # streams keep their exact frame timing (gaps stay gaps unless FILL_GAPS_MS asked for CFR) and their AAC audio as-is
    fpsmode=cfr; aargs=(-c:a aac -b:a 160k)
    if (( live )) && [[ $reason != fill-gaps* ]]; then fpsmode=passthrough; fi
    if (( live )) && [[ $reason != *audio=* ]]; then aargs=(-c:a copy); fi
    nice -n 15 ionice -c 3 ffmpeg -nostdin -hide_banner -loglevel error -y -i "$src" \
      -map 0:v:0 -map '0:a?' \
      -c:v libx264 -preset veryfast -crf 18 -maxrate 30M -bufsize 60M -pix_fmt yuv420p -profile:v high -threads "$ENCODE_THREADS" \
      -vf "$vf" -fps_mode "$fpsmode" "${fpsargs[@]}" \
      "${aargs[@]}" \
      "${tcargs[@]}" -movflags +faststart -f mp4 "$tmp"
  fi
  rc=$?
  d1=$(dur "$src"); d2=$(dur "$tmp")
  if (( rc == 0 )) && [[ -n $d1 && -n $d2 ]] && (( d2 >= d1 - 2 && d2 <= d1 + 2 )); then
    if (( live )); then
      mv -f "$tmp" "$out"; chown 1000:1000 "$out" 2>/dev/null
      if [[ -n $tcjson ]]; then                        # sidecar: exact capture time (read by the Jellyfin plugin) + drift samples
        printf '%s\n' "$tcjson" > "${out%.*}.json"; chown 1000:1000 "${out%.*}.json" 2>/dev/null
      fi
      if [[ $verdict == encode ]] && (( ! deband || KEEP_RAW_STREAMS )); then   # gap-filled re-encode (or asked to): keep the raw in the hidden .src/
        srcdir="$(dirname "$out")/.src"; mkdir -p "$srcdir"; chown 1000:1000 "$srcdir" 2>/dev/null
        mv -f "$src" "$srcdir/$(basename "$out" .mp4).raw.mp4"
      else
        rm -f "$src"                                   # band removal: the cropped file IS the recording; raw-with-band is not kept
      fi
      rmdir "$(dirname "$src")" "$titledir" 2>/dev/null || true   # drop .live and the empty title folder
      vglog info "event=published file=\"$out\" stream=\"$stream\" verdict=$verdict"; continue
    elif (( synced )); then
      rel_src="${src#"$stroot"/}"; rel_out="${out#"$stroot"/}"
      { echo "/$rel_out"; echo "/$rel_src"; } >> "$stroot/.stlocal"   # ignore our output and the raw
      chown 1000:1000 "$stroot/.stlocal" 2>/dev/null
      sleep 2                                           # let Syncthing re-read ignores before the delete
      mv -f "$tmp" "$out"
      rm -f "$src"                                      # raw stays on the gamer's PC; one copy here
    elif [[ $verdict == remux ]]; then
      mv -f "$tmp" "$src"                              # lossless: replace in place
    else
      srcdir="$(dirname "$src")/.src"; mkdir -p "$srcdir"; chown 1000:1000 "$srcdir" 2>/dev/null
      mv -f "$src" "$srcdir/$(basename "$src")"        # keep raw source, hidden from editors/Jellyfin
      mv -f "$tmp" "$out"
    fi
    chown 1000:1000 "$out" 2>/dev/null
    vglog info "event=done file=\"$out\" verdict=$verdict"
  else
    rm -f "$tmp"
    { echo "$(date '+%F %T') $verdict failed rc=$rc src_dur=${d1:-?} out_dur=${d2:-?} ($reason)"; } > "$base.normalize-failed.log"
    vglog error "event=failed file=\"$src\" stream=\"$stream\" verdict=$verdict rc=$rc log=\"$base.normalize-failed.log\"" >&2
  fi
done