#!/usr/bin/env bash
# Convert a RAVDESS speech-only extraction directory tree into a
# rtx-csm manifest.jsonl with proper emotion_tag, transcript, and
# speaker fields (parsed from the filename encoding).
#
# RAVDESS download (208 MB, no auth):
#   curl -L -O https://zenodo.org/records/1188976/files/Audio_Speech_Actors_01-24.zip
#   unzip Audio_Speech_Actors_01-24.zip -d /tmp/ravdess
#
# Filename convention (e.g. `03-01-04-01-02-01-12.wav`):
#   modality (01=AV, 02=video, 03=audio-only)
#   vocal channel (01=speech, 02=song)
#   emotion (01=neutral, 02=calm, 03=happy, 04=sad, 05=angry, 06=fearful, 07=disgust, 08=surprised)
#   intensity (01=normal, 02=strong; neutral has no strong)
#   statement (01="Kids are talking by the door", 02="Dogs are sitting by the door")
#   repetition (01, 02)
#   actor (01..24; odd = male, even = female)
#
# Output schema matches what `examples/steering_extract` expects:
#   {"wav": "<abs path>", "transcript": "...", "emotion_tag": "[neutral]",
#    "speaker": 0|1}
#
# Usage:
#   scripts/build_ravdess_manifest.sh /tmp/ravdess > /tmp/ravdess/manifest.jsonl

set -euo pipefail

ROOT="${1:?usage: $0 <ravdess_root>}"
if [[ ! -d "$ROOT" ]]; then
    echo "not a directory: $ROOT" >&2
    exit 1
fi

# zsh's `read` doesn't have -a, so spawn bash explicitly.
bash -c '
ROOT="$1"
for wav in "$ROOT"/Actor_*/*.wav; do
    base=$(basename "$wav" .wav)
    IFS="-" read -ra parts <<< "$base"
    emo_code="${parts[2]}"
    stmt_code="${parts[4]}"
    actor="${parts[6]}"
    case "$emo_code" in
      01) e="neutral" ;;
      02) e="calm" ;;
      03) e="happy" ;;
      04) e="sad" ;;
      05) e="angry" ;;
      06) e="fearful" ;;
      07) e="disgust" ;;
      08) e="surprised" ;;
      *)  e="unknown" ;;
    esac
    case "$stmt_code" in
      01) t="Kids are talking by the door." ;;
      02) t="Dogs are sitting by the door." ;;
      *)  t="" ;;
    esac
    spk=$((10#$actor % 2))
    jq -nc --arg w "$wav" --arg t "$t" --arg e "$e" --argjson s "$spk" \
      "{wav: \$w, transcript: \$t, emotion_tag: (\"[\" + \$e + \"]\"), speaker: \$s}"
done
' _ "$ROOT"