ml
ca85530b5a
build / build (push) Successful in 2m57s
Preprocessing now tries progressively heavier variants per receipt (plain -> high-pass -> edge-enhance -> both), stopping as soon as a cheap LLM-free arithmetic check on the OCR text looks plausible, so the extra processing only applies to receipts that need it. A flat version of the same heavier processing regressed the full batch by helping hard receipts but hurting easy ones; the adaptive version improves date-matching 37/52 -> 40/52 with no regression (see testing/2026_10_04_gimp_highpass_nlfilter_experiment.md). Also adds test_ocr.sh and test_single.sh for checking a single receipt's OCR text or full pipeline result without a batch run.
97 lines
3.5 KiB
Bash
Executable File
97 lines
3.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Test-only tool: runs the full container pipeline
|
|
# (12_adaptive_preprocess_ocr.sh, 3_extract_data.sh) over every *.jpg in
|
|
# a test-data directory, then compares the results against that
|
|
# directory's ground-truth spreadsheet (benzin_kosten.ods). Everything -
|
|
# preprocessing, OCR, structuring, and the comparison itself - runs
|
|
# inside the tooling container; nothing here depends on a host Python
|
|
# environment.
|
|
#
|
|
# For an input directory <path>/<name>, two sibling directories are
|
|
# created (mirroring <path>/<name>):
|
|
# <path>/<name>-scratch/<receipt>/ - intermediate step output: one
|
|
# variant<N>/ subdir per
|
|
# preprocessing variant tried
|
|
# (01_gray.png, ..., 0X_final.png,
|
|
# ocr.txt each) plus ocr.txt for
|
|
# the winning variant, for
|
|
# inspecting each step on its own
|
|
# <path>/<name>-result/<receipt>/ - final extracted.json per receipt,
|
|
# plus summary.txt with the overall
|
|
# ground-truth comparison
|
|
#
|
|
# Usage: ./test_batch.sh -in <test-data-dir>
|
|
set -euo pipefail
|
|
|
|
cd "$(dirname "${BASH_SOURCE[0]}")"
|
|
ROOT="$(pwd)"
|
|
|
|
fail() { echo "FAIL: $*" >&2; exit 1; }
|
|
|
|
IN_DIR=""
|
|
while [ $# -gt 0 ]; do
|
|
case "$1" in
|
|
-in) IN_DIR="${2:-}"; shift 2 ;;
|
|
*) fail "unknown argument: $1" ;;
|
|
esac
|
|
done
|
|
[ -n "$IN_DIR" ] || fail "usage: $0 -in <test-data-dir>"
|
|
[ -d "$IN_DIR" ] || fail "input directory not found: $IN_DIR"
|
|
|
|
IN_ABS="$(realpath "$IN_DIR")"
|
|
ODS_PATH="$(find "$IN_ABS" -maxdepth 1 -name '*.ods' | head -n1)"
|
|
[ -n "$ODS_PATH" ] || fail "no .ods ground-truth file found in $IN_ABS"
|
|
|
|
PARENT_DIR="$(dirname "$IN_ABS")"
|
|
BASE_NAME="$(basename "$IN_ABS")"
|
|
SCRATCH_DIR="$PARENT_DIR/$BASE_NAME-scratch"
|
|
RESULT_DIR="$PARENT_DIR/$BASE_NAME-result"
|
|
mkdir -p "$SCRATCH_DIR" "$RESULT_DIR"
|
|
|
|
shopt -s nullglob
|
|
IMAGES=("$IN_ABS"/*.jpg)
|
|
[ "${#IMAGES[@]}" -gt 0 ] || fail "no .jpg files found in $IN_ABS"
|
|
|
|
echo "== Running pipeline over ${#IMAGES[@]} receipts =="
|
|
for img in "${IMAGES[@]}"; do
|
|
name="$(basename "${img%.jpg}")"
|
|
receipt_scratch="$SCRATCH_DIR/$name"
|
|
receipt_result="$RESULT_DIR/$name"
|
|
mkdir -p "$receipt_scratch" "$receipt_result"
|
|
echo "--- $name ---"
|
|
./12_adaptive_preprocess_ocr.sh -in "$img" -out "$receipt_scratch" >/dev/null
|
|
./3_extract_data.sh -in "$receipt_scratch/ocr.txt" -out "$receipt_result" >/dev/null
|
|
done
|
|
|
|
echo
|
|
echo "== Comparing against ground truth =="
|
|
|
|
IMAGE="${REGISTRY_IMAGE:-fuelish/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"
|
|
|
|
ODS_DIR="$(dirname "$ODS_PATH")"
|
|
ODS_FILE="$(basename "$ODS_PATH")"
|
|
GROUP_ADD_ARGS=(--group-add "$(stat -c %g "$ODS_DIR")")
|
|
RESULT_GID="$(stat -c %g "$RESULT_DIR")"
|
|
[ "$RESULT_GID" = "$(stat -c %g "$ODS_DIR")" ] || GROUP_ADD_ARGS+=(--group-add "$RESULT_GID")
|
|
|
|
docker run --rm \
|
|
--user "$(id -u):$(id -g)" \
|
|
"${GROUP_ADD_ARGS[@]}" \
|
|
-v "$ODS_DIR:/data/gt:ro" \
|
|
-v "$RESULT_DIR:/data/results:ro" \
|
|
"$IMAGE" \
|
|
python3 /opt/app/src/compare_ground_truth.py -gt "/data/gt/$ODS_FILE" -results /data/results \
|
|
| tee "$RESULT_DIR/summary.txt"
|
|
|
|
echo
|
|
echo "== Done =="
|
|
echo "Intermediate step output: $SCRATCH_DIR/<receipt>/"
|
|
echo "Final results + summary: $RESULT_DIR/<receipt>/, $RESULT_DIR/summary.txt"
|