#!/usr/bin/env bash
# Usage: verify_one_presence.sh SPECIMEN
# SPECIMEN = "species--strain" (Make pattern stem)
# Output: stats/verify_presence/SPECIMEN.stats (one CSV data row, no header)
set -euo pipefail

SPECIMEN="$1"
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
BINARY="${SCRIPT_DIR}/../src/target/release/obikmer"
PYTHON="${SCRIPT_DIR}/../.venv/bin/python3"
VERIFY_PY="${SCRIPT_DIR}/verify_presence.py"

species="${SPECIMEN%%--*}"
strain="${SPECIMEN#*--}"

REF_NPZ="${SCRIPT_DIR}/reference_index/${SPECIMEN}.npz"
INDEX_DIR="${SCRIPT_DIR}/specimen_index_presence/${SPECIMEN}"
STATS_DIR="${SCRIPT_DIR}/stats/verify_presence"
STATS_FILE="${STATS_DIR}/${SPECIMEN}.stats"

mkdir -p "${STATS_DIR}"

echo "[${SPECIMEN}] verifying presence"

"${PYTHON}" "${VERIFY_PY}" \
    --obikmer "${BINARY}" \
    --species "${species}" \
    --strain  "${strain}" \
    "${REF_NPZ}" "${INDEX_DIR}" \
    >"${STATS_FILE}"