Files
breakpilot-lehrer/admin-lehrer/app/(admin)/ai/ocr-pipeline/page.tsx
Benjamin Admin 293e7914d8
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 39s
CI / test-go-edu-search (push) Successful in 27s
CI / test-python-klausur (push) Failing after 1m48s
CI / test-python-agent-core (push) Successful in 17s
CI / test-nodejs-website (push) Successful in 20s
feat: improved OCR pipeline session manager with categories, thumbnails, pipeline logging
- Add document_category (10 types) and pipeline_log JSONB columns
- Session list: thumbnails, copyable IDs, category/doc_type badges
- Inline category dropdown, bulk delete, pipeline step logging
- New endpoints: thumbnail, delete-all, pipeline-log, categories
- Cleared all 22 old test sessions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-05 09:44:38 +01:00

544 lines
22 KiB
TypeScript

'use client'
import { useCallback, useEffect, useState } from 'react'
import { PagePurpose } from '@/components/common/PagePurpose'
import { PipelineStepper } from '@/components/ocr-pipeline/PipelineStepper'
import { StepDeskew } from '@/components/ocr-pipeline/StepDeskew'
import { StepDewarp } from '@/components/ocr-pipeline/StepDewarp'
import { StepColumnDetection } from '@/components/ocr-pipeline/StepColumnDetection'
import { StepRowDetection } from '@/components/ocr-pipeline/StepRowDetection'
import { StepWordRecognition } from '@/components/ocr-pipeline/StepWordRecognition'
import { StepLlmReview } from '@/components/ocr-pipeline/StepLlmReview'
import { StepReconstruction } from '@/components/ocr-pipeline/StepReconstruction'
import { StepGroundTruth } from '@/components/ocr-pipeline/StepGroundTruth'
import { PIPELINE_STEPS, DOCUMENT_CATEGORIES, type PipelineStep, type SessionListItem, type DocumentTypeResult, type DocumentCategory } from './types'
const KLAUSUR_API = '/klausur-api'
export default function OcrPipelinePage() {
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 [docTypeResult, setDocTypeResult] = useState<DocumentTypeResult | null>(null)
const [activeCategory, setActiveCategory] = useState<DocumentCategory | undefined>(undefined)
const [steps, setSteps] = useState<PipelineStep[]>(
PIPELINE_STEPS.map((s, i) => ({
...s,
status: i === 0 ? 'active' : 'pending',
})),
)
// Load session list on mount
useEffect(() => {
loadSessions()
}, [])
const loadSessions = async () => {
setLoadingSessions(true)
try {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions`)
if (res.ok) {
const data = await res.json()
setSessions(data.sessions || [])
}
} catch (e) {
console.error('Failed to load sessions:', e)
} finally {
setLoadingSessions(false)
}
}
const openSession = useCallback(async (sid: string) => {
try {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sid}`)
if (!res.ok) return
const data = await res.json()
setSessionId(sid)
setSessionName(data.name || data.filename || '')
setActiveCategory(data.document_category || undefined)
// Restore doc type result if available
const savedDocType: DocumentTypeResult | null = data.doc_type_result || null
setDocTypeResult(savedDocType)
// Determine which step to jump to based on current_step
const dbStep = data.current_step || 1
// Steps: 1=deskew, 2=dewarp, 3=columns, ...
// UI steps are 0-indexed: 0=deskew, 1=dewarp, 2=columns, ...
const uiStep = Math.max(0, dbStep - 1)
const skipSteps = savedDocType?.skip_steps || []
setSteps(
PIPELINE_STEPS.map((s, i) => ({
...s,
status: skipSteps.includes(s.id)
? 'skipped'
: i < uiStep ? 'completed' : i === uiStep ? 'active' : 'pending',
})),
)
setCurrentStep(uiStep)
} catch (e) {
console.error('Failed to open session:', e)
}
}, [])
const deleteSession = useCallback(async (sid: string) => {
try {
await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sid}`, { method: 'DELETE' })
setSessions((prev) => prev.filter((s) => s.id !== sid))
if (sessionId === sid) {
setSessionId(null)
setCurrentStep(0)
setDocTypeResult(null)
setSteps(PIPELINE_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}
} catch (e) {
console.error('Failed to delete session:', e)
}
}, [sessionId])
const renameSession = useCallback(async (sid: string, newName: string) => {
try {
await fetch(`${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/${sid}`, {
method: 'PUT',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ document_category: category }),
})
setSessions((prev) => prev.map((s) => (s.id === sid ? { ...s, document_category: category } : s)))
if (sessionId === sid) setActiveCategory(category)
} catch (e) {
console.error('Failed to update category:', e)
}
setEditingCategory(null)
}, [sessionId])
const deleteAllSessions = useCallback(async () => {
if (!confirm('Alle Sessions loeschen? Dies kann nicht rueckgaengig gemacht werden.')) return
try {
await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions`, { method: 'DELETE' })
setSessions([])
setSessionId(null)
setCurrentStep(0)
setDocTypeResult(null)
setActiveCategory(undefined)
setSteps(PIPELINE_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
} catch (e) {
console.error('Failed to delete all sessions:', e)
}
}, [])
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) return
// Find the next non-skipped step
const skipSteps = docTypeResult?.skip_steps || []
let nextStep = currentStep + 1
while (nextStep < steps.length && skipSteps.includes(PIPELINE_STEPS[nextStep]?.id)) {
nextStep++
}
if (nextStep >= steps.length) nextStep = steps.length - 1
setSteps((prev) =>
prev.map((s, i) => {
if (i === currentStep) return { ...s, status: 'completed' }
if (i === nextStep) return { ...s, status: 'active' }
// Mark skipped steps between current and next
if (i > currentStep && i < nextStep && skipSteps.includes(PIPELINE_STEPS[i]?.id)) {
return { ...s, status: 'skipped' }
}
return s
}),
)
setCurrentStep(nextStep)
}
const handleDeskewComplete = (sid: string) => {
setSessionId(sid)
// Reload session list to show the new session
loadSessions()
handleNext()
}
const handleDewarpNext = async () => {
// Auto-detect document type after dewarp, then advance
if (sessionId) {
try {
const res = await fetch(
`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}/detect-type`,
{ method: 'POST' },
)
if (res.ok) {
const data: DocumentTypeResult = await res.json()
setDocTypeResult(data)
// Mark skipped steps immediately
const skipSteps = data.skip_steps || []
if (skipSteps.length > 0) {
setSteps((prev) =>
prev.map((s) =>
skipSteps.includes(s.id) ? { ...s, status: 'skipped' } : s,
),
)
}
}
} catch (e) {
console.error('Doc type detection failed:', e)
// Not critical — continue without it
}
}
handleNext()
}
const handleDocTypeChange = (newDocType: DocumentTypeResult['doc_type']) => {
if (!docTypeResult) return
// Build new skip_steps based on doc type
let skipSteps: string[] = []
if (newDocType === 'full_text') {
skipSteps = ['columns', 'rows']
}
// vocab_table and generic_table: no skips
const updated: DocumentTypeResult = {
...docTypeResult,
doc_type: newDocType,
skip_steps: skipSteps,
pipeline: newDocType === 'full_text' ? 'full_page' : 'cell_first',
}
setDocTypeResult(updated)
// Update step statuses
setSteps((prev) =>
prev.map((s) => {
if (skipSteps.includes(s.id)) return { ...s, status: 'skipped' as const }
if (s.status === 'skipped') return { ...s, status: 'pending' as const }
return s
}),
)
}
const handleNewSession = () => {
setSessionId(null)
setSessionName('')
setCurrentStep(0)
setDocTypeResult(null)
setSteps(PIPELINE_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}
const stepNames: Record<number, string> = {
1: 'Begradigung',
2: 'Entzerrung',
3: 'Spalten',
4: 'Zeilen',
5: 'Woerter',
6: 'Korrektur',
7: 'Rekonstruktion',
8: 'Validierung',
}
const reprocessFromStep = useCallback(async (uiStep: number) => {
if (!sessionId) return
const dbStep = uiStep + 1 // UI is 0-indexed, DB is 1-indexed
if (!confirm(`Ab Schritt ${dbStep} (${stepNames[dbStep] || '?'}) neu verarbeiten? Nachfolgende Daten werden geloescht.`)) 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
}
// Reset UI steps
goToStep(uiStep)
} catch (e) {
console.error('Reprocess error:', e)
}
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [sessionId, goToStep])
const renderStep = () => {
switch (currentStep) {
case 0:
return <StepDeskew sessionId={sessionId} onNext={handleDeskewComplete} />
case 1:
return <StepDewarp sessionId={sessionId} onNext={handleDewarpNext} />
case 2:
return <StepColumnDetection sessionId={sessionId} onNext={handleNext} />
case 3:
return <StepRowDetection sessionId={sessionId} onNext={handleNext} />
case 4:
return <StepWordRecognition sessionId={sessionId} onNext={handleNext} goToStep={goToStep} />
case 5:
return <StepLlmReview sessionId={sessionId} onNext={handleNext} />
case 6:
return <StepReconstruction sessionId={sessionId} onNext={handleNext} />
case 7:
return <StepGroundTruth />
default:
return null
}
}
return (
<div className="space-y-6">
<PagePurpose
title="OCR Pipeline"
purpose="Schrittweise Seitenrekonstruktion: Scan begradigen, Spalten erkennen, Woerter lokalisieren und die Seite Wort fuer Wort nachbauen. Ziel: 10 Vokabelseiten fehlerfrei rekonstruieren."
audience={['Entwickler', 'Data Scientists']}
architecture={{
services: ['klausur-service (FastAPI)', 'OpenCV', 'Tesseract'],
databases: ['PostgreSQL Sessions'],
}}
relatedPages={[
{ name: 'OCR Vergleich', href: '/ai/ocr-compare', description: 'Methoden-Vergleich' },
{ name: 'OCR-Labeling', href: '/ai/ocr-labeling', description: 'Trainingsdaten' },
]}
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>
<div className="flex gap-2">
{sessions.length > 0 && (
<button
onClick={deleteAllSessions}
className="text-xs px-3 py-1.5 text-red-600 hover:bg-red-50 dark:hover:bg-red-900/20 rounded-lg transition-colors"
title="Alle Sessions loeschen"
>
Alle loeschen
</button>
)}
<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>
</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>
)}
{/* ID row */}
<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>
<span>Schritt {s.current_step}: {stepNames[s.current_step] || '?'}</span>
</div>
</div>
{/* Badges */}
<div className="flex flex-col gap-1 items-end flex-shrink-0" onClick={(e) => e.stopPropagation()}>
{/* Category Badge */}
<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>
{/* Doc Type Badge (read-only) */}
{s.doc_type && (
<span className="text-[10px] px-1.5 py-0.5 rounded-full bg-gray-100 dark:bg-gray-700 text-gray-500 dark:text-gray-400 border border-gray-200 dark:border-gray-600">
{s.doc_type}
</span>
)}
</div>
{/* Action buttons */}
<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 (inline) */}
{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
})()}
{docTypeResult && (
<span className="text-xs px-2 py-0.5 rounded-full bg-gray-100 dark:bg-gray-700 text-gray-500 dark:text-gray-400 border border-gray-200 dark:border-gray-600">
{docTypeResult.doc_type}
</span>
)}
</div>
)}
<PipelineStepper
steps={steps}
currentStep={currentStep}
onStepClick={handleStepClick}
onReprocess={sessionId ? reprocessFromStep : undefined}
docTypeResult={docTypeResult}
onDocTypeChange={handleDocTypeChange}
/>
<div className="min-h-[400px]">{renderStep()}</div>
</div>
)
}