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>
256 lines
7.1 KiB
TypeScript
256 lines
7.1 KiB
TypeScript
'use client'
|
|
|
|
/**
|
|
* Custom hook encapsulating all state and API logic for the OCR Labeling page.
|
|
*/
|
|
|
|
import { useState, useEffect, useCallback } from 'react'
|
|
import { API_BASE } from './constants'
|
|
import type { OCRSession, OCRItem, OCRStats } from './types'
|
|
|
|
export function useOcrLabeling() {
|
|
const [sessions, setSessions] = useState<OCRSession[]>([])
|
|
const [selectedSession, setSelectedSession] = useState<string | null>(null)
|
|
const [queue, setQueue] = useState<OCRItem[]>([])
|
|
const [currentItem, setCurrentItem] = useState<OCRItem | null>(null)
|
|
const [currentIndex, setCurrentIndex] = useState(0)
|
|
const [stats, setStats] = useState<OCRStats | null>(null)
|
|
const [loading, setLoading] = useState(true)
|
|
const [error, setError] = useState<string | null>(null)
|
|
const [correctedText, setCorrectedText] = useState('')
|
|
const [labelStartTime, setLabelStartTime] = useState<number | null>(null)
|
|
|
|
// Fetch sessions
|
|
const fetchSessions = useCallback(async () => {
|
|
try {
|
|
const res = await fetch(`${API_BASE}/api/v1/ocr-label/sessions`)
|
|
if (res.ok) {
|
|
const data = await res.json()
|
|
setSessions(data)
|
|
}
|
|
} catch (err) {
|
|
console.error('Failed to fetch sessions:', err)
|
|
}
|
|
}, [])
|
|
|
|
// Fetch queue
|
|
const fetchQueue = useCallback(async () => {
|
|
try {
|
|
const url = selectedSession
|
|
? `${API_BASE}/api/v1/ocr-label/queue?session_id=${selectedSession}&limit=20`
|
|
: `${API_BASE}/api/v1/ocr-label/queue?limit=20`
|
|
const res = await fetch(url)
|
|
if (res.ok) {
|
|
const data = await res.json()
|
|
setQueue(data)
|
|
if (data.length > 0 && !currentItem) {
|
|
setCurrentItem(data[0])
|
|
setCurrentIndex(0)
|
|
setCorrectedText(data[0].ocr_text || '')
|
|
setLabelStartTime(Date.now())
|
|
}
|
|
}
|
|
} catch (err) {
|
|
console.error('Failed to fetch queue:', err)
|
|
}
|
|
}, [selectedSession, currentItem])
|
|
|
|
// Fetch stats
|
|
const fetchStats = useCallback(async () => {
|
|
try {
|
|
const url = selectedSession
|
|
? `${API_BASE}/api/v1/ocr-label/stats?session_id=${selectedSession}`
|
|
: `${API_BASE}/api/v1/ocr-label/stats`
|
|
const res = await fetch(url)
|
|
if (res.ok) {
|
|
const data = await res.json()
|
|
setStats(data)
|
|
}
|
|
} catch (err) {
|
|
console.error('Failed to fetch stats:', err)
|
|
}
|
|
}, [selectedSession])
|
|
|
|
// Initial data load
|
|
useEffect(() => {
|
|
const loadData = async () => {
|
|
setLoading(true)
|
|
await Promise.all([fetchSessions(), fetchQueue(), fetchStats()])
|
|
setLoading(false)
|
|
}
|
|
loadData()
|
|
}, [fetchSessions, fetchQueue, fetchStats])
|
|
|
|
// Refresh queue when session changes
|
|
useEffect(() => {
|
|
setCurrentItem(null)
|
|
setCurrentIndex(0)
|
|
fetchQueue()
|
|
fetchStats()
|
|
}, [selectedSession, fetchQueue, fetchStats])
|
|
|
|
// Navigate to next item
|
|
const goToNext = useCallback(() => {
|
|
if (currentIndex < queue.length - 1) {
|
|
const nextIndex = currentIndex + 1
|
|
setCurrentIndex(nextIndex)
|
|
setCurrentItem(queue[nextIndex])
|
|
setCorrectedText(queue[nextIndex].ocr_text || '')
|
|
setLabelStartTime(Date.now())
|
|
} else {
|
|
fetchQueue()
|
|
}
|
|
}, [currentIndex, queue, fetchQueue])
|
|
|
|
// Navigate to previous item
|
|
const goToPrev = useCallback(() => {
|
|
if (currentIndex > 0) {
|
|
const prevIndex = currentIndex - 1
|
|
setCurrentIndex(prevIndex)
|
|
setCurrentItem(queue[prevIndex])
|
|
setCorrectedText(queue[prevIndex].ocr_text || '')
|
|
setLabelStartTime(Date.now())
|
|
}
|
|
}, [currentIndex, queue])
|
|
|
|
// Calculate label time
|
|
const getLabelTime = useCallback((): number | undefined => {
|
|
if (!labelStartTime) return undefined
|
|
return Math.round((Date.now() - labelStartTime) / 1000)
|
|
}, [labelStartTime])
|
|
|
|
// Select a queue item by index
|
|
const selectQueueItem = useCallback((idx: number) => {
|
|
if (idx >= 0 && idx < queue.length) {
|
|
setCurrentIndex(idx)
|
|
setCurrentItem(queue[idx])
|
|
setCorrectedText(queue[idx].ocr_text || '')
|
|
setLabelStartTime(Date.now())
|
|
}
|
|
}, [queue])
|
|
|
|
// Confirm item
|
|
const confirmItem = useCallback(async () => {
|
|
if (!currentItem) return
|
|
|
|
try {
|
|
const res = await fetch(`${API_BASE}/api/v1/ocr-label/confirm`, {
|
|
method: 'POST',
|
|
headers: { 'Content-Type': 'application/json' },
|
|
body: JSON.stringify({
|
|
item_id: currentItem.id,
|
|
label_time_seconds: getLabelTime(),
|
|
}),
|
|
})
|
|
|
|
if (res.ok) {
|
|
setQueue(prev => prev.filter(item => item.id !== currentItem.id))
|
|
goToNext()
|
|
fetchStats()
|
|
} else {
|
|
setError('Bestaetigung fehlgeschlagen')
|
|
}
|
|
} catch {
|
|
setError('Netzwerkfehler')
|
|
}
|
|
}, [currentItem, getLabelTime, goToNext, fetchStats])
|
|
|
|
// Correct item
|
|
const correctItem = useCallback(async () => {
|
|
if (!currentItem || !correctedText.trim()) return
|
|
|
|
try {
|
|
const res = await fetch(`${API_BASE}/api/v1/ocr-label/correct`, {
|
|
method: 'POST',
|
|
headers: { 'Content-Type': 'application/json' },
|
|
body: JSON.stringify({
|
|
item_id: currentItem.id,
|
|
ground_truth: correctedText.trim(),
|
|
label_time_seconds: getLabelTime(),
|
|
}),
|
|
})
|
|
|
|
if (res.ok) {
|
|
setQueue(prev => prev.filter(item => item.id !== currentItem.id))
|
|
goToNext()
|
|
fetchStats()
|
|
} else {
|
|
setError('Korrektur fehlgeschlagen')
|
|
}
|
|
} catch {
|
|
setError('Netzwerkfehler')
|
|
}
|
|
}, [currentItem, correctedText, getLabelTime, goToNext, fetchStats])
|
|
|
|
// Skip item
|
|
const skipItem = useCallback(async () => {
|
|
if (!currentItem) return
|
|
|
|
try {
|
|
const res = await fetch(`${API_BASE}/api/v1/ocr-label/skip`, {
|
|
method: 'POST',
|
|
headers: { 'Content-Type': 'application/json' },
|
|
body: JSON.stringify({ item_id: currentItem.id }),
|
|
})
|
|
|
|
if (res.ok) {
|
|
setQueue(prev => prev.filter(item => item.id !== currentItem.id))
|
|
goToNext()
|
|
fetchStats()
|
|
} else {
|
|
setError('Ueberspringen fehlgeschlagen')
|
|
}
|
|
} catch {
|
|
setError('Netzwerkfehler')
|
|
}
|
|
}, [currentItem, goToNext, fetchStats])
|
|
|
|
// Keyboard shortcuts
|
|
useEffect(() => {
|
|
const handleKeyDown = (e: KeyboardEvent) => {
|
|
if (e.target instanceof HTMLTextAreaElement) return
|
|
|
|
if (e.key === 'Enter' && !e.shiftKey) {
|
|
e.preventDefault()
|
|
confirmItem()
|
|
} else if (e.key === 'ArrowRight') {
|
|
goToNext()
|
|
} else if (e.key === 'ArrowLeft') {
|
|
goToPrev()
|
|
} else if (e.key === 's' && !e.ctrlKey && !e.metaKey) {
|
|
skipItem()
|
|
}
|
|
}
|
|
|
|
window.addEventListener('keydown', handleKeyDown)
|
|
return () => window.removeEventListener('keydown', handleKeyDown)
|
|
}, [confirmItem, goToNext, goToPrev, skipItem])
|
|
|
|
return {
|
|
// State
|
|
sessions,
|
|
selectedSession,
|
|
setSelectedSession,
|
|
queue,
|
|
currentItem,
|
|
currentIndex,
|
|
stats,
|
|
loading,
|
|
error,
|
|
setError,
|
|
correctedText,
|
|
setCorrectedText,
|
|
|
|
// Actions
|
|
fetchSessions,
|
|
fetchQueue,
|
|
fetchStats,
|
|
goToNext,
|
|
goToPrev,
|
|
selectQueueItem,
|
|
confirmItem,
|
|
correctItem,
|
|
skipItem,
|
|
}
|
|
}
|