Files
breakpilot-lehrer/admin-lehrer/app/(admin)/ai/ocr-overlay/page.tsx
Benjamin Admin 3aa4a63257
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 28s
CI / test-go-edu-search (push) Successful in 30s
CI / test-python-klausur (push) Failing after 2m2s
CI / test-python-agent-core (push) Successful in 17s
CI / test-nodejs-website (push) Successful in 18s
fix: move Struktur step after OCR so word boxes are available for exclusion
Graphic detection needs word positions to exclude text from the ink mask.
Previously Struktur ran before OCR, causing every word to be detected as
a graphic element. Now:
- Pipeline: Struktur at index 7 (after Wörter)
- Kombi: Struktur at index 5 (after PP-OCRv5+Tesseract, before Tabelle)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-16 13:38:58 +01:00

549 lines
23 KiB
TypeScript

'use client'
import { useCallback, useEffect, useState } from 'react'
import { PagePurpose } from '@/components/common/PagePurpose'
import { PipelineStepper } from '@/components/ocr-pipeline/PipelineStepper'
import { StepOrientation } from '@/components/ocr-pipeline/StepOrientation'
import { StepDeskew } from '@/components/ocr-pipeline/StepDeskew'
import { StepDewarp } from '@/components/ocr-pipeline/StepDewarp'
import { StepCrop } from '@/components/ocr-pipeline/StepCrop'
import { StepStructureDetection } from '@/components/ocr-pipeline/StepStructureDetection'
import { StepRowDetection } from '@/components/ocr-pipeline/StepRowDetection'
import { StepWordRecognition } from '@/components/ocr-pipeline/StepWordRecognition'
import { OverlayReconstruction } from '@/components/ocr-overlay/OverlayReconstruction'
import { PaddleDirectStep } from '@/components/ocr-overlay/PaddleDirectStep'
import { GridEditor } from '@/components/grid-editor/GridEditor'
import { OVERLAY_PIPELINE_STEPS, PADDLE_DIRECT_STEPS, KOMBI_STEPS, DOCUMENT_CATEGORIES, dbStepToOverlayUi, type PipelineStep, type SessionListItem, type DocumentCategory } from './types'
const KLAUSUR_API = '/klausur-api'
export default function OcrOverlayPage() {
const [mode, setMode] = useState<'pipeline' | 'paddle-direct' | 'kombi'>('pipeline')
const [currentStep, setCurrentStep] = useState(0)
const [sessionId, setSessionId] = useState<string | null>(null)
const [sessionName, setSessionName] = useState<string>('')
const [sessions, setSessions] = useState<SessionListItem[]>([])
const [loadingSessions, setLoadingSessions] = useState(true)
const [editingName, setEditingName] = useState<string | null>(null)
const [editNameValue, setEditNameValue] = useState('')
const [editingCategory, setEditingCategory] = useState<string | null>(null)
const [activeCategory, setActiveCategory] = useState<DocumentCategory | undefined>(undefined)
const [steps, setSteps] = useState<PipelineStep[]>(
OVERLAY_PIPELINE_STEPS.map((s, i) => ({
...s,
status: i === 0 ? 'active' : 'pending',
})),
)
useEffect(() => {
loadSessions()
}, [])
const loadSessions = async () => {
setLoadingSessions(true)
try {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions`)
if (res.ok) {
const data = await res.json()
// Filter to only show top-level sessions (no sub-sessions)
setSessions((data.sessions || []).filter((s: SessionListItem) => !s.parent_session_id))
}
} catch (e) {
console.error('Failed to load sessions:', e)
} finally {
setLoadingSessions(false)
}
}
const openSession = useCallback(async (sid: string) => {
try {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sid}`)
if (!res.ok) return
const data = await res.json()
setSessionId(sid)
setSessionName(data.name || data.filename || '')
setActiveCategory(data.document_category || undefined)
// Check if this session was processed with paddle_direct, kombi, or rapid_kombi
const ocrEngine = data.word_result?.ocr_engine
const isPaddleDirect = ocrEngine === 'paddle_direct'
const isKombi = ocrEngine === 'kombi' || ocrEngine === 'rapid_kombi'
if (isPaddleDirect || isKombi) {
const m = isKombi ? 'kombi' : 'paddle-direct'
const baseSteps = isKombi ? KOMBI_STEPS : PADDLE_DIRECT_STEPS
setMode(m)
// For Kombi: if grid_editor_result exists, jump to grid editor step (6)
// If structure_result exists, jump to grid editor (6)
// If word_result exists, jump to structure step (5)
const hasGrid = isKombi && data.grid_editor_result
const hasStructure = isKombi && data.structure_result
const hasWords = isKombi && data.word_result
const activeStep = hasGrid ? 6 : hasStructure ? 6 : hasWords ? 5 : 4
setSteps(
baseSteps.map((s, i) => ({
...s,
status: i < activeStep ? 'completed' : i === activeStep ? 'active' : 'pending',
})),
)
setCurrentStep(activeStep)
} else {
setMode('pipeline')
// Map DB step to overlay UI step
const dbStep = data.current_step || 1
const uiStep = dbStepToOverlayUi(dbStep)
setSteps(
OVERLAY_PIPELINE_STEPS.map((s, i) => ({
...s,
status: i < uiStep ? 'completed' : i === uiStep ? 'active' : 'pending',
})),
)
setCurrentStep(uiStep)
}
} catch (e) {
console.error('Failed to open session:', e)
}
}, [])
const deleteSession = useCallback(async (sid: string) => {
try {
await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sid}`, { method: 'DELETE' })
setSessions((prev) => prev.filter((s) => s.id !== sid))
if (sessionId === sid) {
setSessionId(null)
setCurrentStep(0)
const baseSteps = mode === 'kombi' ? KOMBI_STEPS : mode === 'paddle-direct' ? PADDLE_DIRECT_STEPS : OVERLAY_PIPELINE_STEPS
setSteps(baseSteps.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}
} catch (e) {
console.error('Failed to delete session:', e)
}
}, [sessionId, mode])
const renameSession = useCallback(async (sid: string, newName: string) => {
try {
await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sid}`, {
method: 'PUT',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ name: newName }),
})
setSessions((prev) => prev.map((s) => (s.id === sid ? { ...s, name: newName } : s)))
if (sessionId === sid) setSessionName(newName)
} catch (e) {
console.error('Failed to rename session:', e)
}
setEditingName(null)
}, [sessionId])
const updateCategory = useCallback(async (sid: string, category: DocumentCategory) => {
try {
await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sid}`, {
method: 'PUT',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ document_category: category }),
})
setSessions((prev) => prev.map((s) => (s.id === sid ? { ...s, document_category: category } : s)))
if (sessionId === sid) setActiveCategory(category)
} catch (e) {
console.error('Failed to update category:', e)
}
setEditingCategory(null)
}, [sessionId])
const handleStepClick = (index: number) => {
if (index <= currentStep || steps[index].status === 'completed') {
setCurrentStep(index)
}
}
const goToStep = (step: number) => {
setCurrentStep(step)
setSteps((prev) =>
prev.map((s, i) => ({
...s,
status: i < step ? 'completed' : i === step ? 'active' : 'pending',
})),
)
}
const handleNext = () => {
if (currentStep >= steps.length - 1) {
// Last step completed — return to session list
const baseSteps = mode === 'kombi' ? KOMBI_STEPS : mode === 'paddle-direct' ? PADDLE_DIRECT_STEPS : OVERLAY_PIPELINE_STEPS
setSteps(baseSteps.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
setCurrentStep(0)
setSessionId(null)
loadSessions()
return
}
const nextStep = currentStep + 1
setSteps((prev) =>
prev.map((s, i) => {
if (i === currentStep) return { ...s, status: 'completed' }
if (i === nextStep) return { ...s, status: 'active' }
return s
}),
)
setCurrentStep(nextStep)
}
const handleOrientationComplete = (sid: string) => {
setSessionId(sid)
loadSessions()
handleNext()
}
const handleNewSession = () => {
setSessionId(null)
setSessionName('')
setCurrentStep(0)
const baseSteps = mode === 'kombi' ? KOMBI_STEPS : mode === 'paddle-direct' ? PADDLE_DIRECT_STEPS : OVERLAY_PIPELINE_STEPS
setSteps(baseSteps.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}
const stepNames: Record<number, string> = {
1: 'Orientierung',
2: 'Begradigung',
3: 'Entzerrung',
4: 'Zuschneiden',
5: 'Zeilen',
6: 'Woerter',
7: 'Overlay',
}
const reprocessFromStep = useCallback(async (uiStep: number) => {
if (!sessionId) return
// Map overlay UI step to DB step
const dbStepMap: Record<number, number> = { 0: 2, 1: 3, 2: 4, 3: 5, 4: 7, 5: 8, 6: 9 }
const dbStep = dbStepMap[uiStep] || uiStep + 1
if (!confirm(`Ab Schritt ${uiStep + 1} (${stepNames[uiStep + 1] || '?'}) neu verarbeiten?`)) return
try {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}/reprocess`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ from_step: dbStep }),
})
if (!res.ok) {
const data = await res.json().catch(() => ({}))
console.error('Reprocess failed:', data.detail || res.status)
return
}
goToStep(uiStep)
} catch (e) {
console.error('Reprocess error:', e)
}
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [sessionId, goToStep])
const renderStep = () => {
if (mode === 'paddle-direct' || mode === 'kombi') {
switch (currentStep) {
case 0:
return <StepOrientation sessionId={sessionId} onNext={handleOrientationComplete} />
case 1:
return <StepDeskew sessionId={sessionId} onNext={handleNext} />
case 2:
return <StepDewarp sessionId={sessionId} onNext={handleNext} />
case 3:
return <StepCrop sessionId={sessionId} onNext={handleNext} />
case 4:
if (mode === 'kombi') {
return (
<PaddleDirectStep
sessionId={sessionId}
onNext={handleNext}
endpoint="paddle-kombi"
title="Kombi-Modus"
description="PP-OCRv5 und Tesseract laufen parallel. Koordinaten werden gewichtet gemittelt fuer optimale Positionierung."
icon="🔀"
buttonLabel="PP-OCRv5 + Tesseract starten"
runningLabel="PP-OCRv5 + Tesseract laufen..."
engineKey="kombi"
/>
)
}
return <PaddleDirectStep sessionId={sessionId} onNext={handleNext} />
case 5:
return mode === 'kombi' ? (
<StepStructureDetection sessionId={sessionId} onNext={handleNext} />
) : null
case 6:
return mode === 'kombi' ? (
<GridEditor sessionId={sessionId} onNext={handleNext} />
) : null
default:
return null
}
}
switch (currentStep) {
case 0:
return <StepOrientation sessionId={sessionId} onNext={handleOrientationComplete} />
case 1:
return <StepDeskew sessionId={sessionId} onNext={handleNext} />
case 2:
return <StepDewarp sessionId={sessionId} onNext={handleNext} />
case 3:
return <StepCrop sessionId={sessionId} onNext={handleNext} />
case 4:
return <StepRowDetection sessionId={sessionId} onNext={handleNext} />
case 5:
return <StepWordRecognition sessionId={sessionId} onNext={handleNext} goToStep={goToStep} skipHealGaps />
case 6:
return <OverlayReconstruction sessionId={sessionId} onNext={handleNext} />
default:
return null
}
}
return (
<div className="space-y-6">
<PagePurpose
title="OCR Overlay"
purpose="Ganzseitige Overlay-Rekonstruktion: Scan begradigen, Zeilen und Woerter erkennen, dann pixelgenau ueber das Bild legen. Ohne Spaltenerkennung — ideal fuer Arbeitsblaetter."
audience={['Entwickler']}
architecture={{
services: ['klausur-service (FastAPI)', 'OpenCV', 'Tesseract'],
databases: ['PostgreSQL Sessions'],
}}
relatedPages={[
{ name: 'OCR Pipeline', href: '/ai/ocr-pipeline', description: 'Volle Pipeline mit Spalten' },
{ name: 'OCR Vergleich', href: '/ai/ocr-compare', description: 'Methoden-Vergleich' },
]}
defaultCollapsed
/>
{/* Session List */}
<div className="bg-white dark:bg-gray-800 rounded-xl border border-gray-200 dark:border-gray-700 p-4">
<div className="flex items-center justify-between mb-3">
<h3 className="text-sm font-medium text-gray-700 dark:text-gray-300">
Sessions ({sessions.length})
</h3>
<button
onClick={handleNewSession}
className="text-xs px-3 py-1.5 bg-teal-600 text-white rounded-lg hover:bg-teal-700 transition-colors"
>
+ Neue Session
</button>
</div>
{loadingSessions ? (
<div className="text-sm text-gray-400 py-2">Lade Sessions...</div>
) : sessions.length === 0 ? (
<div className="text-sm text-gray-400 py-2">Noch keine Sessions vorhanden.</div>
) : (
<div className="space-y-1.5 max-h-[320px] overflow-y-auto">
{sessions.map((s) => {
const catInfo = DOCUMENT_CATEGORIES.find(c => c.value === s.document_category)
return (
<div
key={s.id}
className={`relative flex items-start gap-3 px-3 py-2.5 rounded-lg text-sm transition-colors cursor-pointer ${
sessionId === s.id
? 'bg-teal-50 dark:bg-teal-900/30 border border-teal-200 dark:border-teal-700'
: 'hover:bg-gray-50 dark:hover:bg-gray-700/50'
}`}
>
{/* Thumbnail */}
<div
className="flex-shrink-0 w-12 h-12 rounded-md overflow-hidden bg-gray-100 dark:bg-gray-700"
onClick={() => openSession(s.id)}
>
{/* eslint-disable-next-line @next/next/no-img-element */}
<img
src={`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${s.id}/thumbnail?size=96`}
alt=""
className="w-full h-full object-cover"
loading="lazy"
onError={(e) => { (e.target as HTMLImageElement).style.display = 'none' }}
/>
</div>
{/* Info */}
<div className="flex-1 min-w-0" onClick={() => openSession(s.id)}>
{editingName === s.id ? (
<input
autoFocus
value={editNameValue}
onChange={(e) => setEditNameValue(e.target.value)}
onBlur={() => renameSession(s.id, editNameValue)}
onKeyDown={(e) => {
if (e.key === 'Enter') renameSession(s.id, editNameValue)
if (e.key === 'Escape') setEditingName(null)
}}
onClick={(e) => e.stopPropagation()}
className="w-full px-1 py-0.5 text-sm border rounded dark:bg-gray-700 dark:border-gray-600"
/>
) : (
<div className="truncate font-medium text-gray-700 dark:text-gray-300">
{s.name || s.filename}
</div>
)}
<button
onClick={(e) => {
e.stopPropagation()
navigator.clipboard.writeText(s.id)
const btn = e.currentTarget
btn.textContent = 'Kopiert!'
setTimeout(() => { btn.textContent = `ID: ${s.id.slice(0, 8)}` }, 1500)
}}
className="text-[10px] font-mono text-gray-400 hover:text-teal-500 transition-colors"
title={`Volle ID: ${s.id} — Klick zum Kopieren`}
>
ID: {s.id.slice(0, 8)}
</button>
<div className="text-xs text-gray-400 flex gap-2 mt-0.5">
<span>{new Date(s.created_at).toLocaleDateString('de-DE', { day: '2-digit', month: '2-digit', year: '2-digit', hour: '2-digit', minute: '2-digit' })}</span>
</div>
</div>
{/* Category Badge */}
<div className="flex flex-col gap-1 items-end flex-shrink-0" onClick={(e) => e.stopPropagation()}>
<button
onClick={() => setEditingCategory(editingCategory === s.id ? null : s.id)}
className={`text-[10px] px-1.5 py-0.5 rounded-full border transition-colors ${
catInfo
? 'bg-teal-50 dark:bg-teal-900/30 border-teal-200 dark:border-teal-700 text-teal-700 dark:text-teal-300'
: 'bg-gray-50 dark:bg-gray-700 border-gray-200 dark:border-gray-600 text-gray-400 hover:text-gray-600 dark:hover:text-gray-300'
}`}
title="Kategorie setzen"
>
{catInfo ? `${catInfo.icon} ${catInfo.label}` : '+ Kategorie'}
</button>
</div>
{/* Actions */}
<div className="flex flex-col gap-0.5 flex-shrink-0">
<button
onClick={(e) => {
e.stopPropagation()
setEditNameValue(s.name || s.filename)
setEditingName(s.id)
}}
className="p-1 text-gray-400 hover:text-gray-600 dark:hover:text-gray-300"
title="Umbenennen"
>
<svg className="w-3.5 h-3.5" fill="none" viewBox="0 0 24 24" stroke="currentColor" strokeWidth={2}>
<path strokeLinecap="round" strokeLinejoin="round" d="M15.232 5.232l3.536 3.536m-2.036-5.036a2.5 2.5 0 113.536 3.536L6.5 21.036H3v-3.572L16.732 3.732z" />
</svg>
</button>
<button
onClick={(e) => {
e.stopPropagation()
if (confirm('Session loeschen?')) deleteSession(s.id)
}}
className="p-1 text-gray-400 hover:text-red-500"
title="Loeschen"
>
<svg className="w-3.5 h-3.5" fill="none" viewBox="0 0 24 24" stroke="currentColor" strokeWidth={2}>
<path strokeLinecap="round" strokeLinejoin="round" d="M19 7l-.867 12.142A2 2 0 0116.138 21H7.862a2 2 0 01-1.995-1.858L5 7m5 4v6m4-6v6m1-10V4a1 1 0 00-1-1h-4a1 1 0 00-1 1v3M4 7h16" />
</svg>
</button>
</div>
{/* Category dropdown */}
{editingCategory === s.id && (
<div
className="absolute right-0 top-full mt-1 z-20 bg-white dark:bg-gray-800 border border-gray-200 dark:border-gray-700 rounded-lg shadow-lg p-2 grid grid-cols-2 gap-1 w-64"
onClick={(e) => e.stopPropagation()}
>
{DOCUMENT_CATEGORIES.map((cat) => (
<button
key={cat.value}
onClick={() => updateCategory(s.id, cat.value)}
className={`text-xs px-2 py-1.5 rounded-md text-left transition-colors ${
s.document_category === cat.value
? 'bg-teal-100 dark:bg-teal-900/40 text-teal-700 dark:text-teal-300'
: 'hover:bg-gray-100 dark:hover:bg-gray-700 text-gray-600 dark:text-gray-400'
}`}
>
{cat.icon} {cat.label}
</button>
))}
</div>
)}
</div>
)
})}
</div>
)}
</div>
{/* Active session info */}
{sessionId && sessionName && (
<div className="flex items-center gap-3 text-sm text-gray-500 dark:text-gray-400">
<span>Aktive Session: <span className="font-medium text-gray-700 dark:text-gray-300">{sessionName}</span></span>
{activeCategory && (() => {
const cat = DOCUMENT_CATEGORIES.find(c => c.value === activeCategory)
return cat ? <span className="text-xs px-2 py-0.5 rounded-full bg-teal-50 dark:bg-teal-900/30 border border-teal-200 dark:border-teal-700 text-teal-700 dark:text-teal-300">{cat.icon} {cat.label}</span> : null
})()}
</div>
)}
{/* Mode Toggle */}
<div className="flex items-center gap-1 bg-gray-100 dark:bg-gray-800 rounded-lg p-1 w-fit">
<button
onClick={() => {
if (mode === 'pipeline') return
setMode('pipeline')
setCurrentStep(0)
setSessionId(null)
setSteps(OVERLAY_PIPELINE_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}}
className={`px-3 py-1.5 text-xs font-medium rounded-md transition-colors ${
mode === 'pipeline'
? 'bg-white dark:bg-gray-700 text-gray-700 dark:text-gray-200 shadow-sm'
: 'text-gray-500 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300'
}`}
>
Pipeline (7 Schritte)
</button>
<button
onClick={() => {
if (mode === 'paddle-direct') return
setMode('paddle-direct')
setCurrentStep(0)
setSessionId(null)
setSteps(PADDLE_DIRECT_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}}
className={`px-3 py-1.5 text-xs font-medium rounded-md transition-colors ${
mode === 'paddle-direct'
? 'bg-white dark:bg-gray-700 text-gray-700 dark:text-gray-200 shadow-sm'
: 'text-gray-500 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300'
}`}
>
PP-OCRv5 Direct (5 Schritte)
</button>
<button
onClick={() => {
if (mode === 'kombi') return
setMode('kombi')
setCurrentStep(0)
setSessionId(null)
setSteps(KOMBI_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}}
className={`px-3 py-1.5 text-xs font-medium rounded-md transition-colors ${
mode === 'kombi'
? 'bg-white dark:bg-gray-700 text-gray-700 dark:text-gray-200 shadow-sm'
: 'text-gray-500 dark:text-gray-400 hover:text-gray-700 dark:hover:text-gray-300'
}`}
>
Kombi (7 Schritte)
</button>
</div>
<PipelineStepper
steps={steps}
currentStep={currentStep}
onStepClick={handleStepClick}
onReprocess={mode === 'pipeline' && sessionId != null ? reprocessFromStep : undefined}
/>
<div className="min-h-[400px]">{renderStep()}</div>
</div>
)
}