feat: add Kombi-Modus (PaddleOCR + Tesseract) for OCR Overlay
Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 35s
CI / test-go-edu-search (push) Successful in 33s
CI / test-python-klausur (push) Failing after 2m20s
CI / test-python-agent-core (push) Successful in 22s
CI / test-nodejs-website (push) Successful in 41s

Runs both OCR engines on the preprocessed image and merges results:
word boxes matched by IoU, coordinates averaged by confidence weight.
Unmatched Tesseract words (bullets, symbols) are added for better coverage.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-03-12 20:05:50 +01:00
parent d335a7bbf3
commit e9ccd1e35c
4 changed files with 279 additions and 26 deletions

View File

@@ -10,14 +10,38 @@ type Phase = 'idle' | 'running' | 'overlay'
interface PaddleDirectStepProps {
sessionId: string | null
onNext: () => void
/** Backend endpoint suffix, default: 'paddle-direct' */
endpoint?: string
/** Title shown in idle state */
title?: string
/** Description shown in idle state */
description?: string
/** Icon shown in idle state */
icon?: string
/** Button label */
buttonLabel?: string
/** Running label */
runningLabel?: string
/** OCR engine key to check for auto-detect */
engineKey?: string
}
export function PaddleDirectStep({ sessionId, onNext }: PaddleDirectStepProps) {
export function PaddleDirectStep({
sessionId,
onNext,
endpoint = 'paddle-direct',
title = 'Paddle Direct',
description = 'PaddleOCR erkennt alle Woerter direkt auf dem Originalbild — ohne Begradigung, Entzerrung oder Zuschnitt.',
icon = '⚡',
buttonLabel = 'PaddleOCR starten',
runningLabel = 'PaddleOCR laeuft...',
engineKey = 'paddle_direct',
}: PaddleDirectStepProps) {
const [phase, setPhase] = useState<Phase>('idle')
const [error, setError] = useState<string | null>(null)
const [stats, setStats] = useState<{ cells: number; rows: number; duration: number } | null>(null)
// Auto-detect: if session already has paddle_direct word_result → show overlay
// Auto-detect: if session already has matching word_result → show overlay
useEffect(() => {
if (!sessionId) return
let cancelled = false
@@ -26,7 +50,7 @@ export function PaddleDirectStep({ sessionId, onNext }: PaddleDirectStepProps) {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}`)
if (!res.ok || cancelled) return
const data = await res.json()
if (data.word_result?.ocr_engine === 'paddle_direct') {
if (data.word_result?.ocr_engine === engineKey) {
setPhase('overlay')
}
} catch {
@@ -34,14 +58,14 @@ export function PaddleDirectStep({ sessionId, onNext }: PaddleDirectStepProps) {
}
})()
return () => { cancelled = true }
}, [sessionId])
}, [sessionId, engineKey])
const runPaddleDirect = useCallback(async () => {
const runOcr = useCallback(async () => {
if (!sessionId) return
setPhase('running')
setError(null)
try {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}/paddle-direct`, {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}/${endpoint}`, {
method: 'POST',
})
if (!res.ok) {
@@ -59,7 +83,7 @@ export function PaddleDirectStep({ sessionId, onNext }: PaddleDirectStepProps) {
setError(e instanceof Error ? e.message : 'Unbekannter Fehler')
setPhase('idle')
}
}, [sessionId])
}, [sessionId, endpoint])
if (!sessionId) {
return (
@@ -91,7 +115,7 @@ export function PaddleDirectStep({ sessionId, onNext }: PaddleDirectStepProps) {
<div className="w-10 h-10 border-4 border-teal-200 dark:border-teal-800 border-t-teal-600 dark:border-t-teal-400 rounded-full animate-spin" />
<div className="text-center space-y-1">
<p className="text-sm font-medium text-gray-700 dark:text-gray-300">
PaddleOCR laeuft...
{runningLabel}
</p>
<p className="text-xs text-gray-400">
Bild wird analysiert (ca. 5-30s)
@@ -101,12 +125,12 @@ export function PaddleDirectStep({ sessionId, onNext }: PaddleDirectStepProps) {
) : (
<>
<div className="text-center space-y-2">
<div className="text-4xl"></div>
<div className="text-4xl">{icon}</div>
<h3 className="text-lg font-medium text-gray-700 dark:text-gray-300">
Paddle Direct
{title}
</h3>
<p className="text-sm text-gray-500 dark:text-gray-400 max-w-md">
PaddleOCR erkennt alle Woerter direkt auf dem Originalbild ohne Begradigung, Entzerrung oder Zuschnitt.
{description}
</p>
</div>
@@ -117,10 +141,10 @@ export function PaddleDirectStep({ sessionId, onNext }: PaddleDirectStepProps) {
)}
<button
onClick={runPaddleDirect}
onClick={runOcr}
className="px-6 py-2.5 bg-teal-600 text-white text-sm font-medium rounded-lg hover:bg-teal-700 transition-colors"
>
PaddleOCR starten
{buttonLabel}
</button>
</>
)}