#!/usr/bin/env bash
# Test-only tool: runs preprocessing + OCR (1_preprocess_image.sh,
# 2_ocr_image.sh - variant 0/baseline only, deliberately not
# 12_adaptive_preprocess_ocr.sh) on a single receipt photo and prints the
# raw OCR text to stdout - no LLM extraction step, no ground-truth
# comparison, and no files left behind (unlike test_single.sh/
# test_batch.sh, which persist scratch/result directories and go through
# the real adaptive pipeline). Useful for quickly checking what Tesseract
# actually reads off one specific preprocessing variant in isolation -
# e.g. while iterating on tooling-container/src/preprocess.py - without
# the adaptive step's variant selection in the way, waiting on the LLM
# call, or needing ground truth.
#
# Usage: ./test_ocr.sh -in <photo.jpg>
set -euo pipefail

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

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

IN_PATH=""
while [ $# -gt 0 ]; do
    case "$1" in
        -in) IN_PATH="${2:-}"; shift 2 ;;
        *) fail "unknown argument: $1" ;;
    esac
done
[ -n "$IN_PATH" ] || fail "usage: $0 -in <photo.jpg>"
[ -f "$IN_PATH" ] || fail "input file not found: $IN_PATH"

SCRATCH_DIR="$(mktemp -d)"
trap 'rm -rf "$SCRATCH_DIR"' EXIT

./1_preprocess_image.sh -in "$IN_PATH" -out "$SCRATCH_DIR" >/dev/null
./2_ocr_image.sh -in "$SCRATCH_DIR/03_final.png" -out "$SCRATCH_DIR" >/dev/null

cat "$SCRATCH_DIR/ocr.txt"