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

agents/fedeo-device-agent/tests/scan.test.ts

@@ -51,6 +51,7 @@ const setup = async (t: TestContext) => {
         workDir: path.join(dir, "scans with 100% space"), scannerName: "fujitsu:ScanSnap iX1600:test",
         scanFormat: "pdf", scanResolution: 300, scanMode: "Color", scanSource: "ADF Duplex",
         scanTimeoutSeconds: 10, scanPostprocess: false, postprocessProfile: "document",
+        scanBackgroundCleanup: false, scanOcr: false, scanOcrLanguage: "deu+eng",
         postprocessPython: "python3", postprocessStrict: false,
     }
     const job: ScanJob = { id: "test-job", tenantId: 1, agentId: "test-agent", status: "running", settings: { paperSize: "A4" } }
@@ -143,6 +144,18 @@ test("missing image runtime is detected before feeding paper", async (t) => {
     await assert.rejects(args(), /ENOENT/)
 })
 
+test("missing requested OCR language fails before the scanner consumes paper", async (t) => {
+    const { config, job, dir, args } = await setup(t)
+    const tesseract = path.join(dir, "tesseract")
+    await writeFile(tesseract, "#!/bin/sh\nprintf 'List of available languages (1):\\neng\\n'\n")
+    await chmod(tesseract, 0o755)
+    job.settings!.ocr = true
+    job.settings!.ocrLanguage = "deu+eng"
+    await assert.rejects(runScan(config, job), /OCR-Sprachpakete fehlen: deu/)
+    await assert.rejects(args(), /ENOENT/)
+    await assert.rejects(readdir(config.workDir), /ENOENT/)
+})
+
 test("single-page scans work without batch and requested paths cannot escape the job directory", async (t) => {
     const { config, job, args } = await setup(t)
     job.settings = { source: "Flatbed", format: "png" }