Add containerized OCR pipeline for fuel receipts

Self-hosted, verifiable pipeline for extracting structured data (station,
date/time, price per litre, litres, discount, total) from German fuel
receipt photos: grayscale + mild bilateral filter + contrast stretch,
Tesseract OCR, then LLM structuring via a small local model (Qwen 2.5,
served by Ollama). Each step is independently runnable and inspectable
through numbered scripts against a shared tooling container.

Ollama runs as its own long-lived container (0_run_ollama.sh), separate
from the stateless per-receipt pipeline steps, so the model stays loaded
in memory between runs. Includes a containerized ground-truth batch test
(test_batch.sh) that reproduces the full pipeline over the test receipts
and reports per-field accuracy.

Targets eventual deployment on a Raspberry Pi 4 k3s cluster.

test_batch.sh

@@ -0,0 +1,94 @@
+#!/usr/bin/env bash
+# Test-only tool: runs the full container pipeline (1_preprocess_image.sh,
+# 2_ocr_image.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
+#                                       (01_gray.png, 02_bilateral.png,
+#                                       03_final.png, ocr.txt) 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 "--- $name ---"
+    ./1_preprocess_image.sh -in "$img" -out "$receipt_scratch" >/dev/null
+    ./2_ocr_image.sh -in "$receipt_scratch/03_final.png" -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:-gastronomy/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"