feat(scan): whiten receipt backgrounds and embed OCR in PDFs

agents/fedeo-device-agent/tests/scan_ocr_test.py

@@ -0,0 +1,71 @@
+import shutil
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import patch
+
+from PIL import Image, ImageDraw, ImageFont, PdfParser
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1] / "scripts"))
+from scan_document import create_document, check_ocr
+
+
+class ScanOcrTest(unittest.TestCase):
+    def test_missing_language_is_reported_before_processing(self):
+        with patch("scan_document.run_ocr_command", return_value="List of available languages (1):\neng\n"):
+            with self.assertRaisesRegex(RuntimeError, "deu"):
+                check_ocr("deu+eng")
+        with self.assertRaises(ValueError):
+            check_ocr("--bad-language")
+
+    @unittest.skipUnless(shutil.which("tesseract") and shutil.which("pdftotext"), "Tesseract and Poppler required")
+    def test_ocr_keeps_receipt_canvas_blank_back_and_page_order_with_real_extractable_text(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            pages = []
+            for index, text in enumerate(["FEDEO Bon 12345", "", "Zweite Seite 24680"]):
+                page = root / f"page-{index}.png"
+                image = Image.new("RGB", (1240, 1754), (45, 45, 45) if index == 0 else "white")
+                draw = ImageDraw.Draw(image)
+                if index == 0:
+                    draw.rectangle((260, 150, 1000, 1550), fill="white")
+                if text:
+                    draw.text((300, 300), text, fill="black", font=ImageFont.load_default(size=44))
+                    draw.text((300, 390), "Summe EUR 12,34", fill="black", font=ImageFont.load_default(size=36))
+                image.save(page)
+                pages.append(page)
+            output = root / "searchable.pdf"
+            result = create_document(pages, output, 150, ocr=True, background_cleanup=True)
+            self.assertEqual(result["pageCount"], 3)
+            with PdfParser.PdfParser(filename=str(output)) as pdf:
+                self.assertEqual(len(pdf.pages), 3)
+                for reference in pdf.pages:
+                    box = pdf.read_indirect(reference)[b"MediaBox"]
+                    self.assertAlmostEqual(box[2], 1240 * 72 / 150, delta=.1)
+                    self.assertAlmostEqual(box[3], 1754 * 72 / 150, delta=.1)
+            text = subprocess.check_output(["pdftotext", str(output), "-"], text=True)
+            extracted = text.split("\f")
+            self.assertIn("12345", extracted[0])
+            self.assertEqual(extracted[1].strip(), "")
+            self.assertIn("24680", extracted[2])
+            self.assertTrue(all(page.exists() for page in pages))
+
+    def test_ocr_failure_never_publishes_a_partial_document_or_removes_raw_pages(self):
+        with tempfile.TemporaryDirectory() as directory:
+            root = Path(directory)
+            page = root / "raw.png"
+            Image.new("RGB", (400, 600), "white").save(page)
+            output = root / "failed.pdf"
+            with patch("scan_document.check_ocr"), patch("scan_document.run_ocr_command", side_effect=RuntimeError("OCR failed")):
+                with self.assertRaisesRegex(RuntimeError, "OCR failed"):
+                    create_document([page], output, 300, ocr=True)
+            self.assertFalse(output.exists())
+            self.assertFalse(output.with_name("failed.pdf.partial").exists())
+            self.assertTrue(page.exists())
+            self.assertEqual(list(root.glob("prepared-*")), [])
+
+
+if __name__ == "__main__":
+    unittest.main()