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.
95 lines
3.4 KiB
Bash
Executable File
95 lines
3.4 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) on a single receipt
|
|
# photo - the test_batch.sh equivalent for re-checking one receipt (e.g.
|
|
# a known failure, after a preprocessing/prompt tweak) without re-running
|
|
# a whole directory. If a ground-truth spreadsheet (*.ods) is found next
|
|
# to the photo, compares the result against it the same way
|
|
# test_batch.sh does; otherwise just prints the extracted JSON.
|
|
# Everything - preprocessing, OCR, structuring, and the comparison itself
|
|
# - runs inside the tooling container; nothing here depends on a host
|
|
# Python environment.
|
|
#
|
|
# For an input photo <path>/<name>.jpg, two sibling directories are
|
|
# created (mirroring test_batch.sh's layout, just for one receipt):
|
|
# <path>/<name>-scratch/<name>/ - intermediate step output: one
|
|
# variant<N>/ subdir per preprocessing
|
|
# variant tried, plus ocr.txt for the
|
|
# winning variant
|
|
# <path>/<name>-result/<name>/ - extracted.json, plus summary.txt
|
|
# if a ground-truth .ods was found
|
|
#
|
|
# Usage: ./test_single.sh -in <photo.jpg>
|
|
set -euo pipefail
|
|
|
|
cd "$(dirname "${BASH_SOURCE[0]}")"
|
|
ROOT="$(pwd)"
|
|
|
|
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: $IN_PATH"
|
|
|
|
IN_ABS="$(realpath "$IN_PATH")"
|
|
IN_DIR="$(dirname "$IN_ABS")"
|
|
NAME="$(basename "${IN_ABS%.jpg}")"
|
|
|
|
SCRATCH_DIR="$IN_DIR/$NAME-scratch"
|
|
RESULT_DIR="$IN_DIR/$NAME-result"
|
|
receipt_scratch="$SCRATCH_DIR/$NAME"
|
|
receipt_result="$RESULT_DIR/$NAME"
|
|
mkdir -p "$receipt_scratch" "$receipt_result"
|
|
|
|
echo "== Running pipeline on $NAME =="
|
|
./12_adaptive_preprocess_ocr.sh -in "$IN_ABS" -out "$receipt_scratch" >/dev/null
|
|
./3_extract_data.sh -in "$receipt_scratch/ocr.txt" -out "$receipt_result" >/dev/null
|
|
|
|
echo
|
|
echo "== Extracted =="
|
|
cat "$receipt_result/extracted.json"
|
|
echo
|
|
|
|
ODS_PATH="$(find "$IN_DIR" -maxdepth 1 -name '*.ods' | head -n1)"
|
|
if [ -n "$ODS_PATH" ]; then
|
|
echo
|
|
echo "== Comparing against ground truth =="
|
|
|
|
IMAGE="${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"
|
|
else
|
|
echo "(no ground-truth .ods found next to $IN_PATH - skipping comparison)"
|
|
fi
|
|
|
|
echo
|
|
echo "== Done =="
|
|
echo "Intermediate step output: $receipt_scratch/"
|
|
echo "Final result: $receipt_result/extracted.json"
|