#!/usr/bin/env bash
# Kaisa (sof-rt5682) HDMI stability probe.
# Goal: one script to reproduce/quantify "reboot -> silent -> later OK" and capture
# kernel SOF IPC(-5)/ASoC errors with monotonic timestamps.
#
# What it does (non-destructive, no service stop by default):
# - Repeatedly tries playback on HiFi HDMI sinks (pcm=2/3/4 as requested)
# - After each attempt, scrapes *new* kernel lines for SOF/ASoC HDMI hw_params failures
# - Records ALSA subdevices availability, Jack/ELD states, default sink, and sinks list
#
# Logs:
#   ./_logs/kaisa-hdmi-stability-probe_<ts>.log  (or $KAISA_LOG_DIR)
#
# Notes:
# - Run as desktop user (no sudo). Needs access to kernel journal for best results.
# - If journalctl -k is restricted, the script will still log PipeWire errors and ALSA state.
set -euo pipefail

ts="$(date +%Y%m%d_%H%M%S)"
log_dir="${KAISA_LOG_DIR:-./_logs}"
out="${log_dir}/kaisa-hdmi-stability-probe_${ts}.log"

duration_s="${KAISA_PROBE_DURATION_S:-120}"
interval_s="${KAISA_PROBE_INTERVAL_S:-2}"
pcms="${KAISA_PROBE_PCMS:-2,3}" # comma-separated list: 2,3,4
audio_file="${KAISA_PROBE_AUDIO_FILE:-/usr/share/sounds/alsa/Front_Center.wav}"

usage() {
  cat <<'EOF'
Usage:
  ./scripts/kaisa-hdmi-stability-probe.sh [--duration S] [--interval S] [--pcms 2,3,4]

Env overrides:
  KAISA_LOG_DIR
  KAISA_PROBE_DURATION_S
  KAISA_PROBE_INTERVAL_S
  KAISA_PROBE_PCMS
  KAISA_PROBE_AUDIO_FILE

Example:
  KAISA_PROBE_DURATION_S=180 KAISA_PROBE_PCMS=2,3 ./scripts/kaisa-hdmi-stability-probe.sh
EOF
}

while [[ $# -gt 0 ]]; do
  case "$1" in
    -h|--help) usage; exit 0 ;;
    --duration) duration_s="${2:?seconds}"; shift 2 ;;
    --interval) interval_s="${2:?seconds}"; shift 2 ;;
    --pcms) pcms="${2:?list}"; shift 2 ;;
    *) echo "Unknown arg: $1" >&2; usage >&2; exit 2 ;;
  esac
done

mkdir -p "$log_dir"
exec > >(tee "$out") 2>&1

hr() { printf '\n%s\n' "================================================================================"; }
sec() { hr; printf '%s\n' "$1"; hr; }
note() { printf '\n[NOTE] %s\n' "$*"; }
warn() { printf '\n[WARN] %s\n' "$*"; }

kernel_grep_re='sof-audio|sof_ipc3_pcm_hw_params|ipc tx error|STREAM_PCM_PARAMS|ASoC error|HDMI1|HDMI2|HDMI3|pcm2|pcm3|pcm4'
pipewire_grep_re='set_hw_params|suspended -> error|Start error|hw_sofrt5682_[234]__sink'

get_default_sink() {
  pactl info 2>/dev/null | awk -F': ' '/^默认音频入口:|^Default Sink:/{print $2; exit}'
}

list_sinks_short() {
  pactl list short sinks 2>/dev/null || true
}

alsa_dump_subdevices() {
  aplay -l 2>/dev/null | awk '
    BEGIN { dev=""; }
    $0 ~ /^card [0-9]+: / { next }
    $0 ~ /, device [0-9]+: / {
      match($0, /device [0-9]+:/)
      dev=substr($0, RSTART+7, RLENGTH-8)
      gsub(/[^0-9]/,"",dev)
      print $0
      next
    }
    $0 ~ /(子设备:|Subdevices:)/ {
      print "  " $0
      next
    }
  '
}

amixer_dump_jack_eld() {
  # Stable numids for this platform are often: Jack 10/16/22; ELD 15/21/27.
  # If they differ, doctor script can resolve dynamically; here we best-effort.
  for n in 10 16 22 15 21 27; do
    echo
    echo "\$ amixer -c0 cget numid=$n"
    amixer -c0 cget "numid=$n" 2>/dev/null || true
  done
}

kernel_tail_since() {
  # Print kernel lines since a monotonic timestamp (string like "[   78.312861]")
  # We do not rely on exact parse; we simply filter journalctl -k -b -o short-monotonic output
  # by lexicographic comparison on the bracketed numeric value.
  local since="${1:-}"
  if ! journalctl -k -b -o short-monotonic --no-pager &>/dev/null; then
    note "Cannot read kernel journal (journalctl -k)."
    return 0
  fi
  if [[ -z "$since" ]]; then
    journalctl -k -b -o short-monotonic --no-pager | grep -E "$kernel_grep_re" | tail -n 80 || true
    return 0
  fi
  journalctl -k -b -o short-monotonic --no-pager | awk -v since="$since" '
    # since is like "[   78.312861]"
    function num(s,   x) {
      x=s
      gsub(/[\[\]]/,"",x)
      gsub(/^[[:space:]]+/,"",x)
      return x+0.0
    }
    {
      tag=""
      if (match($0, /^\[[^]]+\]/)) {
        tag=substr($0, RSTART, RLENGTH)
      }
      if (tag != "" && num(tag) >= num(since)) print $0
    }
  ' | grep -E "$kernel_grep_re" | tail -n 120 || true
}

now_monotonic() {
  # Current kernel journal last monotonic tag, best-effort.
  # journalctl -o short-monotonic lines start with: "[    3.588851] ..."
  # which may tokenize as "[" "3.588851]" ... so we must extract up to the first "]".
  journalctl -k -b -o short-monotonic --no-pager 2>/dev/null | tail -n 1 | \
    awk '{ if (match($0, /^\[[^]]+\]/)) print substr($0, RSTART, RLENGTH); }' || true
}

play_on_pcm() {
  local pcm="${1:?pcm}"
  local sink="alsa_output.pci-0000_00_1f.3-platform-cml_rt5682_def.HiFi__hw_sofrt5682_${pcm}__sink"
  echo
  echo "\$ pactl set-default-sink $sink"
  pactl set-default-sink "$sink" 2>/dev/null || true
  echo "\$ pw-play $audio_file"
  timeout -k 1s 5s pw-play "$audio_file" 2>/dev/null || true
}

sec "Kaisa HDMI stability probe — report: $out"
echo "\$ date"; date
echo "\$ uname -a"; uname -a
echo "\$ id"; id
echo
note "duration_s=$duration_s interval_s=$interval_s pcms=$pcms audio_file=$audio_file"
note "Tip: run right after reboot, before any manual audio tweaks."

sec "Baseline: ALSA + Jack/ELD + sinks"
echo "\$ aplay -l"; aplay -l || true
echo
echo "\$ aplay -l (subdevices summary)"; alsa_dump_subdevices || true
sec "Jack/ELD (best-effort numid dump)"
amixer_dump_jack_eld
sec "PipeWire sinks"
echo "\$ pactl info"; pactl info || true
echo "\$ pactl list short sinks"; list_sinks_short

start_epoch="$(date +%s)"
end_epoch="$((start_epoch + duration_s))"
iter=0

last_mon="$(now_monotonic)"
note "Kernel monotonic cursor (initial): ${last_mon:-<none>}"

sec "Loop"
while [[ "$(date +%s)" -lt "$end_epoch" ]]; do
  iter="$((iter+1))"
  echo
  hr
  echo "[ITER $iter] time=$(date) default_sink=$(get_default_sink || true)"

  # Try play on each requested pcm
  IFS=',' read -r -a pcm_arr <<< "$pcms"
  for pcm in "${pcm_arr[@]}"; do
    pcm="$(echo "$pcm" | tr -d '[:space:]')"
    [[ -n "$pcm" ]] || continue
    play_on_pcm "$pcm"
  done

  echo
  echo "[ITER $iter] sinks:"
  list_sinks_short

  echo
  echo "[ITER $iter] new kernel hints since ${last_mon:-<none>}:"
  new_kernel="$(kernel_tail_since "${last_mon:-}")"
  if [[ -n "${new_kernel}" ]]; then
    warn "Kernel SOF/ASoC lines (tail):"
    printf '%s\n' "${new_kernel}"
  else
    echo "(none)"
  fi

  # Advance cursor
  last_mon="$(now_monotonic)"

  sleep "$interval_s"
done

sec "Done"
note "Saved: $out"
note "If you hit failures, also capture: journalctl -k -b -o short-monotonic | grep -nE '$kernel_grep_re' | tail -n 200"