Files
breakpilot-lehrer/admin-lehrer/app/(admin)/ai/ocr-labeling/page.tsx
Benjamin Admin b681ddb131 [split-required] Split 58 monoliths across Python, Go, TypeScript (Phases 1-3)
Phase 1 — Python (klausur-service): 5 monoliths → 36 files
- dsfa_corpus_ingestion.py (1,828 LOC → 5 files)
- cv_ocr_engines.py (2,102 LOC → 7 files)
- cv_layout.py (3,653 LOC → 10 files)
- vocab_worksheet_api.py (2,783 LOC → 8 files)
- grid_build_core.py (1,958 LOC → 6 files)

Phase 2 — Go (edu-search-service, school-service): 8 monoliths → 19 files
- staff_crawler.go (1,402 → 4), policy/store.go (1,168 → 3)
- policy_handlers.go (700 → 2), repository.go (684 → 2)
- search.go (592 → 2), ai_extraction_handlers.go (554 → 2)
- seed_data.go (591 → 2), grade_service.go (646 → 2)

Phase 3 — TypeScript (admin-lehrer): 45 monoliths → 220+ files
- sdk/types.ts (2,108 → 16 domain files)
- ai/rag/page.tsx (2,686 → 14 files)
- 22 page.tsx files split into _components/ + _hooks/
- 11 component files split into sub-components
- 10 SDK data catalogs added to loc-exceptions
- Deleted dead backup index_original.ts (4,899 LOC)

All original public APIs preserved via re-export facades.
Zero new errors: Python imports verified, Go builds clean,
TypeScript tsc --noEmit shows only pre-existing errors.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-24 17:28:57 +02:00

146 lines
5.4 KiB
TypeScript

'use client'
/**
* OCR Labeling Admin Page
*
* Labeling interface for handwriting training data collection.
* DSGVO-konform: Alle Verarbeitung lokal auf Mac Mini (Ollama).
*
* Teil der KI-Daten-Pipeline:
* OCR-Labeling → RAG Pipeline → Daten & RAG
*/
import { useState } from 'react'
import { PagePurpose } from '@/components/common/PagePurpose'
import { AIModuleSidebarResponsive } from '@/components/ai/AIModuleSidebar'
import { tabs, type TabId } from './constants'
import { useOcrLabeling } from './useOcrLabeling'
import { LabelingTab } from './_components/LabelingTab'
import { SessionsTab } from './_components/SessionsTab'
import { UploadTab } from './_components/UploadTab'
import { StatsTab } from './_components/StatsTab'
import { ExportTab } from './_components/ExportTab'
export default function OCRLabelingPage() {
const [activeTab, setActiveTab] = useState<TabId>('labeling')
const hook = useOcrLabeling()
return (
<div className="p-6">
{/* Header */}
<div className="mb-6">
<h1 className="text-2xl font-bold text-gray-900 dark:text-white">OCR-Labeling</h1>
<p className="text-gray-600 dark:text-gray-400">Handschrift-Training & Ground Truth Erfassung</p>
</div>
{/* Page Purpose with Related Pages */}
<PagePurpose
title="OCR-Labeling"
purpose="Erstellen Sie Ground Truth Daten für das Training von Handschrift-Erkennungsmodellen. Labeln Sie OCR-Ergebnisse, korrigieren Sie Fehler und exportieren Sie Trainingsdaten für TrOCR, Llama Vision und andere Modelle. Teil der KI-Daten-Pipeline: Gelabelte Daten können zur RAG Pipeline exportiert werden."
audience={['Entwickler', 'Data Scientists', 'QA-Team']}
architecture={{
services: ['klausur-service (Python)'],
databases: ['PostgreSQL', 'MinIO (Bilder)'],
}}
relatedPages={[
{ name: 'Magic Help', href: '/ai/magic-help', description: 'TrOCR testen & fine-tunen' },
{ name: 'RAG Pipeline', href: '/ai/rag-pipeline', description: 'Trainierte Daten indexieren' },
{ name: 'Klausur-Korrektur', href: '/ai/klausur-korrektur', description: 'OCR in Aktion' },
{ name: 'Daten & RAG', href: '/ai/rag', description: 'Indexierte Daten durchsuchen' },
]}
collapsible={true}
defaultCollapsed={true}
/>
{/* AI Module Sidebar - Desktop: Fixed, Mobile: FAB + Drawer */}
<AIModuleSidebarResponsive currentModule="ocr-labeling" />
{/* Error Toast */}
{hook.error && (
<div className="fixed top-4 right-4 bg-red-100 border border-red-400 text-red-700 px-4 py-3 rounded z-50">
<span>{hook.error}</span>
<button onClick={() => hook.setError(null)} className="ml-4">X</button>
</div>
)}
{/* Tabs */}
<div className="mb-6">
<div className="border-b border-slate-200">
<nav className="flex space-x-4" aria-label="Tabs">
{tabs.map((tab) => (
<button
key={tab.id}
onClick={() => setActiveTab(tab.id)}
className={`flex items-center gap-2 px-4 py-3 border-b-2 font-medium text-sm transition-colors ${
activeTab === tab.id
? 'border-primary-500 text-primary-600'
: 'border-transparent text-slate-500 hover:text-slate-700 hover:border-slate-300'
}`}
>
{tab.icon}
{tab.name}
</button>
))}
</nav>
</div>
</div>
{/* Tab Content */}
{hook.loading ? (
<div className="flex items-center justify-center h-64">
<div className="animate-spin rounded-full h-8 w-8 border-b-2 border-primary-600" />
</div>
) : (
<>
{activeTab === 'labeling' && (
<LabelingTab
queue={hook.queue}
currentItem={hook.currentItem}
currentIndex={hook.currentIndex}
correctedText={hook.correctedText}
setCorrectedText={hook.setCorrectedText}
goToNext={hook.goToNext}
goToPrev={hook.goToPrev}
selectQueueItem={hook.selectQueueItem}
confirmItem={hook.confirmItem}
correctItem={hook.correctItem}
skipItem={hook.skipItem}
/>
)}
{activeTab === 'sessions' && (
<SessionsTab
sessions={hook.sessions}
selectedSession={hook.selectedSession}
setSelectedSession={hook.setSelectedSession}
fetchSessions={hook.fetchSessions}
setError={hook.setError}
/>
)}
{activeTab === 'upload' && (
<UploadTab
sessions={hook.sessions}
selectedSession={hook.selectedSession}
setSelectedSession={hook.setSelectedSession}
fetchQueue={hook.fetchQueue}
fetchStats={hook.fetchStats}
setError={hook.setError}
/>
)}
{activeTab === 'stats' && (
<StatsTab stats={hook.stats} />
)}
{activeTab === 'export' && (
<ExportTab
sessions={hook.sessions}
selectedSession={hook.selectedSession}
setSelectedSession={hook.setSelectedSession}
stats={hook.stats}
setError={hook.setError}
/>
)}
</>
)}
</div>
)
}