#!/usr/bin/env sh
# Stage 2-1 ordered runner: build the two datasets that stage 2-2 consumes.
#   1) SEP  -> head_ident_scoring_dataset/SEP/sep_head_ident.jsonl
#   2) FocalLora -> head_ident_scoring_dataset/FocalLora/focal_lora_dataset_all_combined.json
set -eu

CONDA_BIN=${CONDA_BIN:-}
if [ -z "$CONDA_BIN" ]; then
  if command -v conda >/dev/null 2>&1; then
    CONDA_BIN=$(command -v conda)
  elif [ -x /opt/miniconda/bin/conda ]; then
    CONDA_BIN=/opt/miniconda/bin/conda
  fi
fi
if [ -n "$CONDA_BIN" ]; then
  eval "$("$CONDA_BIN" shell.bash hook)"
  conda activate focallora4
fi

SCRIPT_DIR=$(CDPATH= cd -- "$(dirname -- "$0")" && pwd)
DS_DIR="$SCRIPT_DIR/head_ident_scoring_dataset"

echo "[2-1] Building SEP head-identification dataset ..."
python "$DS_DIR/SEP/2_convert_SEP_to_head_ident.py"

echo "[2-1] Building FocalLora dataset ..."
sh "$DS_DIR/FocalLora/focallora_gendata.sh"

echo "[2-1] Done."