#!/usr/bin/env bash
set -euo pipefail

# Offline runner for determinism (and optional reachability) benches.
# Usage: ./offline_run.sh [--inputs DIR] [--output DIR] [--runs N] [--threshold FLOAT] [--no-verify]
# Defaults: inputs=offline/inputs, output=offline/results, runs=10, threshold=0.95, verify manifests on.

ROOT="$(cd "$(dirname "$0")" && pwd)"
INPUT_DIR="offline/inputs"
OUTPUT_DIR="offline/results"
RUNS=10
THRESHOLD=0.95
VERIFY=1

while [[ $# -gt 0 ]]; do
  case "$1" in
    --inputs) INPUT_DIR="$2"; shift 2;;
    --output) OUTPUT_DIR="$2"; shift 2;;
    --runs) RUNS="$2"; shift 2;;
    --threshold) THRESHOLD="$2"; shift 2;;
    --no-verify) VERIFY=0; shift 1;;
    *) echo "Unknown arg: $1"; exit 1;;
  esac
done

mkdir -p "$OUTPUT_DIR"
cd "$ROOT"

if [ $VERIFY -eq 1 ]; then
  if [ -f "$INPUT_DIR/inputs.sha256" ]; then
    sha256sum -c "$INPUT_DIR/inputs.sha256"
  fi
  if [ -f "$INPUT_DIR/dataset.sha256" ]; then
    sha256sum -c "$INPUT_DIR/dataset.sha256"
  fi
fi

python run_bench.py \
  --sboms "$INPUT_DIR"/sboms/*.json \
  --vex "$INPUT_DIR"/vex/*.json \
  --config "$INPUT_DIR"/scanners.json \
  --runs "$RUNS" \
  --shuffle \
  --output "$OUTPUT_DIR"

det_rate=$(python -c "import json;print(json.load(open('$OUTPUT_DIR/summary.json'))['determinism_rate'])")
awk -v rate="$det_rate" -v th="$THRESHOLD" 'BEGIN {if (rate+0 < th+0) {printf("determinism_rate %s is below threshold %s\n", rate, th); exit 1}}'

graph_glob="$INPUT_DIR/graphs/*.json"
runtime_glob="$INPUT_DIR/runtime/*.ndjson"
if ls $graph_glob >/dev/null 2>&1; then
  python run_reachability.py \
    --graphs "$graph_glob" \
    --runtime "$runtime_glob" \
    --output "$OUTPUT_DIR"
fi

echo "Offline run complete -> $OUTPUT_DIR"