flfeders/FEDEO
2
1
Fork 0
Code Issues 116 Pull Requests Actions Packages Projects 23 Releases 20 Wiki Activity

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

Browse Source
This commit is contained in:
Florian Federspiel
2026-09-24 17:41:30 +02:00
parent b9cfdbe29e
commit a65bd72d74
26 changed files with 572 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
agents/fedeo-device-agent/src/scan/postprocess.ts
View File

@@ -6,15 +6,34 @@ import { runCommand } from "../commands.js"
const agentRoot = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "../..")
const documentScript = path.join(agentRoot, "scripts/scan_document.py")
export const checkScanRuntime = async (config: AgentConfig, postprocess: boolean) => {
const imports = postprocess && config.postprocessStrict ? "import PIL, cv2, numpy" : "import PIL"
type ProcessingOptions = { ocr: boolean; ocrLanguage: string; backgroundCleanup: boolean }
export const checkScanRuntime = async (config: AgentConfig, postprocess: boolean, options: ProcessingOptions) => {
const args = [documentScript, "--check-runtime", "--ocr-language", options.ocrLanguage]
if (postprocess) args.push("--postprocess")
if (config.postprocessStrict) args.push("--strict")
if (options.backgroundCleanup) args.push("--background-cleanup")
if (options.ocr) args.push("--ocr")
try {
const result = await runCommand(config.postprocessPython, ["-c", imports], { timeoutMs: 10_000 })
const result = await runCommand(config.postprocessPython, args, { timeoutMs: 10_000 })
if (result.code === 0) return
} catch {
throw new Error(result.stderr.trim())
} catch (error) {
// Report missing runtimes before the scanner consumes any paper.
const detail = error instanceof Error ? error.message : String(error)
throw new Error("Scan-Verarbeitung nicht verfügbar. Bitte den Agenten mit Python/Pillow, OpenCV und Tesseract samt OCR-Sprachpaketen installieren. " + detail)
}
throw new Error("Python/Pillow (bei strikter Nachbearbeitung zusätzlich OpenCV) fehlt. Bitte npm run setup:opencv ausführen oder python3-pil installieren.")
}
export const processingCapabilities = async (config: AgentConfig) => {
const available = async (options: ProcessingOptions) => {
try { await checkScanRuntime(config, false, options); return true } catch { return false }
}
const [ocr, backgroundCleanup] = await Promise.all([
available({ ocr: true, ocrLanguage: config.scanOcrLanguage, backgroundCleanup: false }),
available({ ocr: false, ocrLanguage: config.scanOcrLanguage, backgroundCleanup: true }),
])
return { ocr, backgroundCleanup }
}
export const createScanDocument = async (
@@ -23,11 +42,14 @@ export const createScanDocument = async (
outputPath: string,
resolution: number,
postprocess: boolean,
profile: AgentConfig["postprocessProfile"]
profile: AgentConfig["postprocessProfile"],
options: ProcessingOptions
): Promise<ScanResult> => {
const args = [documentScript, "--output", outputPath, "--resolution", String(resolution), "--profile", profile]
if (postprocess) args.push("--postprocess")
if (config.postprocessStrict) args.push("--strict")
if (options.backgroundCleanup) args.push("--background-cleanup")
if (options.ocr) args.push("--ocr", "--ocr-language", options.ocrLanguage)
args.push("--inputs", ...pages)
const result = await runCommand(config.postprocessPython, args, {