#!/usr/bin/env bash
# Step 3 of the pipeline: send raw OCR text to a small text-only LLM
# (served by Ollama on the host) to structure it into the receipt JSON
# schema. Runs with --network host so the container can reach Ollama at
# 127.0.0.1 on the host; override with OLLAMA_URL / OLLAMA_MODEL env vars
# if Ollama runs elsewhere or you want a different model.
#
# Usage: ./3_extract_data.sh -in <ocr.txt> -out <scratch-dir>
set -euo pipefail

cd "$(dirname "${BASH_SOURCE[0]}")"
ROOT="$(pwd)"

fail() { echo "FAIL: $*" >&2; exit 1; }

IN_PATH=""
OUT_DIR=""
while [ $# -gt 0 ]; do
    case "$1" in
        -in) IN_PATH="${2:-}"; shift 2 ;;
        -out) OUT_DIR="${2:-}"; shift 2 ;;
        *) fail "unknown argument: $1" ;;
    esac
done
[ -n "$IN_PATH" ] && [ -n "$OUT_DIR" ] \
    || fail "usage: $0 -in <ocr.txt> -out <scratch-dir>"
[ -f "$IN_PATH" ] || fail "input file not found: $IN_PATH"

command -v docker >/dev/null 2>&1 || fail "docker not found in PATH"

IMAGE="${REGISTRY_IMAGE:-gastronomy/tools}"
if [ -f "$ROOT/registry.env" ]; then
    # shellcheck disable=SC1091
    source "$ROOT/registry.env"
    IMAGE="${REGISTRY_IMAGE:-$IMAGE}"
fi
VERSION="$(<"$ROOT/tooling-container/VERSION")"
IMAGE="$IMAGE:$VERSION"
docker image inspect "$IMAGE" >/dev/null 2>&1 \
    || fail "$IMAGE not found locally - run ./build-image.sh first"

IN_ABS="$(realpath "$IN_PATH")"
IN_DIR="$(dirname "$IN_ABS")"
IN_FILE="$(basename "$IN_ABS")"
mkdir -p "$OUT_DIR"
OUT_ABS="$(realpath "$OUT_DIR")"

# On a vboxsf-mounted repo, files are owned by root:vboxsf with no
# "other" access - join the mounted dirs' groups so --user can read/write
# them without needing root inside the container.
GROUP_ADD_ARGS=(--group-add "$(stat -c %g "$IN_DIR")")
OUT_GID="$(stat -c %g "$OUT_ABS")"
[ "$OUT_GID" = "$(stat -c %g "$IN_DIR")" ] || GROUP_ADD_ARGS+=(--group-add "$OUT_GID")

echo "== Extracting structured data from $IN_FILE =="
docker run --rm \
    --network host \
    --user "$(id -u):$(id -g)" \
    "${GROUP_ADD_ARGS[@]}" \
    -e OLLAMA_URL="${OLLAMA_URL:-http://127.0.0.1:11434/api/chat}" \
    -e OLLAMA_MODEL="${OLLAMA_MODEL:-qwen2.5:3b}" \
    -v "$IN_DIR:/data/in:ro" \
    -v "$OUT_ABS:/data/out" \
    "$IMAGE" \
    python3 /opt/app/src/extract.py -in "/data/in/$IN_FILE" -out /data/out

echo "== Done =="
echo "Extracted JSON written to: $OUT_ABS/extracted.json"