feat: OCR Overlay — ganzseitige Rekonstruktion ohne Spaltenerkennung
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 31s
CI / test-go-edu-search (push) Successful in 33s
CI / test-python-klausur (push) Failing after 2m6s
CI / test-python-agent-core (push) Successful in 20s
CI / test-nodejs-website (push) Successful in 28s

Neue Route /ai/ocr-overlay mit vereinfachter 7-Schritt-Pipeline
(Orientierung, Begradigung, Entzerrung, Zuschnitt, Zeilen, Woerter, Overlay).
Nutzt bestehende Step-Komponenten, ueberspringt Spalten/LLM-Review/Ground-Truth.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-03-11 00:08:05 +01:00
parent 840918df2a
commit 2cbdfc56f3
5 changed files with 1253 additions and 0 deletions

View File

@@ -0,0 +1,423 @@
'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 { StepRowDetection } from '@/components/ocr-pipeline/StepRowDetection'
import { StepWordRecognition } from '@/components/ocr-pipeline/StepWordRecognition'
import { OverlayReconstruction } from '@/components/ocr-overlay/OverlayReconstruction'
import { OVERLAY_PIPELINE_STEPS, DOCUMENT_CATEGORIES, dbStepToOverlayUi, type PipelineStep, type SessionListItem, type DocumentCategory } from './types'
const KLAUSUR_API = '/klausur-api'
export default function OcrOverlayPage() {
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/${sid}`)
if (!res.ok) return
const data = await res.json()
setSessionId(sid)
setSessionName(data.name || data.filename || '')
setActiveCategory(data.document_category || undefined)
// Map DB step to overlay UI step
const dbStep = data.current_step || 1
const uiStep = dbStepToOverlayUi(dbStep)
setSteps(
OVERLAY_PIPELINE_STEPS.map((s, i) => ({
...s,
status: i < uiStep ? 'completed' : i === uiStep ? 'active' : 'pending',
})),
)
setCurrentStep(uiStep)
} catch (e) {
console.error('Failed to open session:', e)
}
}, [])
const deleteSession = useCallback(async (sid: string) => {
try {
await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sid}`, { method: 'DELETE' })
setSessions((prev) => prev.filter((s) => s.id !== sid))
if (sessionId === sid) {
setSessionId(null)
setCurrentStep(0)
setSteps(OVERLAY_PIPELINE_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}
} catch (e) {
console.error('Failed to delete session:', e)
}
}, [sessionId])
const renameSession = useCallback(async (sid: string, newName: string) => {
try {
await fetch(`${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 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
setSteps(OVERLAY_PIPELINE_STEPS.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)
setSteps(OVERLAY_PIPELINE_STEPS.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 = () => {
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} />
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>
)}
<PipelineStepper
steps={steps}
currentStep={currentStep}
onStepClick={handleStepClick}
onReprocess={sessionId ? reprocessFromStep : undefined}
/>
<div className="min-h-[400px]">{renderStep()}</div>
</div>
)
}

View File

@@ -0,0 +1,60 @@
import type { PipelineStep } from '../ocr-pipeline/types'
// Re-export types used by overlay components
export type {
PipelineStep,
PipelineStepStatus,
SessionListItem,
SessionInfo,
DocumentCategory,
DocumentTypeResult,
OrientationResult,
CropResult,
DeskewResult,
DewarpResult,
RowResult,
RowItem,
GridResult,
GridCell,
WordBbox,
ColumnMeta,
} from '../ocr-pipeline/types'
export { DOCUMENT_CATEGORIES } from '../ocr-pipeline/types'
/**
* 7-step pipeline for full-page overlay reconstruction.
* Skips: Spalten (columns), LLM-Review (Korrektur), Ground-Truth (Validierung)
*/
export const OVERLAY_PIPELINE_STEPS: PipelineStep[] = [
{ id: 'orientation', name: 'Orientierung', icon: '🔄', status: 'pending' },
{ id: 'deskew', name: 'Begradigung', icon: '📐', status: 'pending' },
{ id: 'dewarp', name: 'Entzerrung', icon: '🔧', status: 'pending' },
{ id: 'crop', name: 'Zuschneiden', icon: '✂️', status: 'pending' },
{ id: 'rows', name: 'Zeilen', icon: '📏', status: 'pending' },
{ id: 'words', name: 'Woerter', icon: '🔤', status: 'pending' },
{ id: 'reconstruction', name: 'Overlay', icon: '🏗️', status: 'pending' },
]
/** Map from overlay UI step index to DB step number (1-indexed) */
export const OVERLAY_UI_TO_DB: Record<number, number> = {
0: 2, // orientation
1: 3, // deskew
2: 4, // dewarp
3: 5, // crop
4: 6, // rows (skip columns=6 in DB, rows=7 — but we reuse DB step numbering)
5: 7, // words
6: 9, // reconstruction
}
/** Map from DB step to overlay UI step index */
export function dbStepToOverlayUi(dbStep: number): number {
// DB: 1=start, 2=orient, 3=deskew, 4=dewarp, 5=crop, 6=columns, 7=rows, 8=words, 9=recon, 10=gt
if (dbStep <= 2) return 0 // orientation
if (dbStep === 3) return 1 // deskew
if (dbStep === 4) return 2 // dewarp
if (dbStep === 5) return 3 // crop
if (dbStep <= 7) return 4 // rows (skip columns)
if (dbStep === 8) return 5 // words
return 6 // reconstruction
}

View File

@@ -0,0 +1,576 @@
'use client'
import { useCallback, useEffect, useMemo, useRef, useState } from 'react'
import type { GridResult, GridCell, RowResult, RowItem } from '@/app/(admin)/ai/ocr-overlay/types'
import { usePixelWordPositions } from './usePixelWordPositions'
const KLAUSUR_API = '/klausur-api'
interface OverlayReconstructionProps {
sessionId: string | null
onNext: () => void
}
interface EditableCell {
cellId: string
text: string
originalText: string
bboxPct: { x: number; y: number; w: number; h: number }
colType: string
rowIndex: number
colIndex: number
}
type UndoAction = { cellId: string; oldText: string; newText: string }
export function OverlayReconstruction({ sessionId, onNext }: OverlayReconstructionProps) {
const [status, setStatus] = useState<'loading' | 'ready' | 'saving' | 'saved' | 'error'>('loading')
const [error, setError] = useState('')
const [cells, setCells] = useState<EditableCell[]>([])
const [gridCells, setGridCells] = useState<GridCell[]>([])
const [editedTexts, setEditedTexts] = useState<Map<string, string>>(new Map())
// Undo/Redo
const [undoStack, setUndoStack] = useState<UndoAction[]>([])
const [redoStack, setRedoStack] = useState<UndoAction[]>([])
// Overlay state
const [rows, setRows] = useState<RowItem[]>([])
const [imageNaturalSize, setImageNaturalSize] = useState<{ w: number; h: number } | null>(null)
const [fontScale, setFontScale] = useState(0.7)
const [globalBold, setGlobalBold] = useState(false)
const [imageRotation, setImageRotation] = useState<0 | 180>(0)
const reconRef = useRef<HTMLDivElement>(null)
const [reconWidth, setReconWidth] = useState(0)
// Pixel-based word positions
const overlayImageUrl = sessionId
? `${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}/image/cropped`
: ''
const cellWordPositions = usePixelWordPositions(
overlayImageUrl,
gridCells,
status === 'ready',
imageRotation,
)
// Track container width
useEffect(() => {
const el = reconRef.current
if (!el) return
const obs = new ResizeObserver(entries => {
for (const entry of entries) setReconWidth(entry.contentRect.width)
})
obs.observe(el)
return () => obs.disconnect()
}, [status])
// Load session data
useEffect(() => {
if (!sessionId) return
loadSessionData()
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [sessionId])
const loadSessionData = async () => {
if (!sessionId) return
setStatus('loading')
try {
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}`)
if (!res.ok) throw new Error(`HTTP ${res.status}`)
const data = await res.json()
const wordResult: GridResult | undefined = data.word_result
if (!wordResult) {
setError('Keine Worterkennungsdaten gefunden. Bitte zuerst den Woerter-Schritt abschliessen.')
setStatus('error')
return
}
const rawGridCells: GridCell[] = wordResult.cells || []
setGridCells(rawGridCells)
const editableCells: EditableCell[] = rawGridCells.map(c => ({
cellId: c.cell_id,
text: c.text,
originalText: c.text,
bboxPct: c.bbox_pct,
colType: c.col_type,
rowIndex: c.row_index,
colIndex: c.col_index,
}))
setCells(editableCells)
setEditedTexts(new Map())
setUndoStack([])
setRedoStack([])
// Load rows
const rowResult: RowResult | undefined = data.row_result
if (rowResult?.rows) setRows(rowResult.rows)
// Store image dimensions
if (wordResult.image_width && wordResult.image_height) {
setImageNaturalSize({ w: wordResult.image_width, h: wordResult.image_height })
}
setStatus('ready')
} catch (e: unknown) {
setError(e instanceof Error ? e.message : String(e))
setStatus('error')
}
}
const handleTextChange = useCallback((cellId: string, newText: string) => {
setEditedTexts(prev => {
const oldText = prev.get(cellId)
const cell = cells.find(c => c.cellId === cellId)
const prevText = oldText ?? cell?.text ?? ''
setUndoStack(stack => [...stack, { cellId, oldText: prevText, newText }])
setRedoStack([])
const next = new Map(prev)
next.set(cellId, newText)
return next
})
}, [cells])
const undo = useCallback(() => {
setUndoStack(stack => {
if (stack.length === 0) return stack
const action = stack[stack.length - 1]
const newStack = stack.slice(0, -1)
setRedoStack(rs => [...rs, action])
setEditedTexts(prev => {
const next = new Map(prev)
next.set(action.cellId, action.oldText)
return next
})
return newStack
})
}, [])
const redo = useCallback(() => {
setRedoStack(stack => {
if (stack.length === 0) return stack
const action = stack[stack.length - 1]
const newStack = stack.slice(0, -1)
setUndoStack(us => [...us, action])
setEditedTexts(prev => {
const next = new Map(prev)
next.set(action.cellId, action.newText)
return next
})
return newStack
})
}, [])
const resetCell = useCallback((cellId: string) => {
setEditedTexts(prev => {
const next = new Map(prev)
next.delete(cellId)
return next
})
}, [])
// Keyboard shortcuts
useEffect(() => {
const handler = (e: KeyboardEvent) => {
if ((e.metaKey || e.ctrlKey) && e.key === 'z') {
e.preventDefault()
if (e.shiftKey) redo()
else undo()
}
}
document.addEventListener('keydown', handler)
return () => document.removeEventListener('keydown', handler)
}, [undo, redo])
const getDisplayText = useCallback((cell: EditableCell): string => {
return editedTexts.get(cell.cellId) ?? cell.text
}, [editedTexts])
const isEdited = useCallback((cell: EditableCell): boolean => {
const edited = editedTexts.get(cell.cellId)
return edited !== undefined && edited !== cell.originalText
}, [editedTexts])
const changedCount = useMemo(() => {
let count = 0
for (const cell of cells) {
if (isEdited(cell)) count++
}
return count
}, [cells, isEdited])
// Tab navigation
const sortedCellIds = useMemo(() => {
return [...cells]
.sort((a, b) => a.rowIndex !== b.rowIndex ? a.rowIndex - b.rowIndex : a.colIndex - b.colIndex)
.map(c => c.cellId)
}, [cells])
const handleKeyDown = useCallback((e: React.KeyboardEvent, cellId: string) => {
if (e.key === 'Tab') {
e.preventDefault()
const idx = sortedCellIds.indexOf(cellId)
const nextIdx = e.shiftKey ? idx - 1 : idx + 1
if (nextIdx >= 0 && nextIdx < sortedCellIds.length) {
const nextId = sortedCellIds[nextIdx]
const el = document.getElementById(`cell-${nextId}`)
el?.focus()
}
}
}, [sortedCellIds])
const saveReconstruction = useCallback(async () => {
if (!sessionId) return
setStatus('saving')
try {
const cellUpdates = Array.from(editedTexts.entries())
.filter(([cellId, text]) => {
const cell = cells.find(c => c.cellId === cellId)
return cell && text !== cell.originalText
})
.map(([cellId, text]) => ({ cell_id: cellId, text }))
if (cellUpdates.length === 0) {
setStatus('saved')
return
}
const res = await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}/reconstruction`, {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ cells: cellUpdates }),
})
if (!res.ok) {
const data = await res.json().catch(() => ({}))
throw new Error(data.detail || `HTTP ${res.status}`)
}
setStatus('saved')
} catch (e: unknown) {
setError(e instanceof Error ? e.message : String(e))
setStatus('error')
}
}, [sessionId, editedTexts, cells])
const dewarpedUrl = sessionId
? `${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sessionId}/image/cropped`
: ''
if (!sessionId) {
return <div className="text-center py-12 text-gray-400">Bitte zuerst eine Session auswaehlen.</div>
}
if (status === 'loading') {
return (
<div className="flex items-center gap-3 justify-center py-12">
<div className="animate-spin rounded-full h-5 w-5 border-b-2 border-teal-500" />
<span className="text-gray-500">Overlay-Daten werden geladen...</span>
</div>
)
}
if (status === 'error') {
return (
<div className="flex flex-col items-center justify-center py-12 text-center">
<div className="text-5xl mb-4">&#x26A0;&#xFE0F;</div>
<h3 className="text-lg font-medium text-red-600 dark:text-red-400 mb-2">Fehler</h3>
<p className="text-sm text-gray-500 dark:text-gray-400 max-w-lg mb-4">{error}</p>
<div className="flex gap-3">
<button onClick={() => { setError(''); loadSessionData() }}
className="px-5 py-2 bg-teal-600 text-white rounded-lg hover:bg-teal-700 transition-colors text-sm">
Erneut versuchen
</button>
<button onClick={onNext}
className="px-5 py-2 bg-gray-200 dark:bg-gray-700 text-gray-700 dark:text-gray-300 rounded-lg hover:bg-gray-300 dark:hover:bg-gray-600 transition-colors text-sm">
Ueberspringen &rarr;
</button>
</div>
</div>
)
}
if (status === 'saved') {
return (
<div className="flex flex-col items-center justify-center py-12 text-center">
<div className="text-5xl mb-4">&#x2705;</div>
<h3 className="text-lg font-medium text-gray-700 dark:text-gray-300 mb-2">Overlay gespeichert</h3>
<p className="text-sm text-gray-500 dark:text-gray-400 mb-6">
{changedCount > 0 ? `${changedCount} Zellen wurden aktualisiert.` : 'Keine Aenderungen vorgenommen.'}
</p>
<button onClick={onNext}
className="px-6 py-2.5 bg-teal-600 text-white rounded-lg hover:bg-teal-700 transition-colors font-medium">
Fertig
</button>
</div>
)
}
const imgW = imageNaturalSize?.w || 1
const imgH = imageNaturalSize?.h || 1
const containerH = reconWidth * (imgH / imgW)
return (
<div className="space-y-3">
{/* Toolbar */}
<div className="flex items-center justify-between bg-white dark:bg-gray-800 rounded-lg border border-gray-200 dark:border-gray-700 px-3 py-2">
<div className="flex items-center gap-2">
<h3 className="text-sm font-medium text-gray-700 dark:text-gray-300">
Overlay-Rekonstruktion
</h3>
<span className="text-xs text-gray-400">
{cells.length} Zellen &middot; {changedCount} geaendert
</span>
</div>
<div className="flex items-center gap-2">
{/* Undo/Redo */}
<button
onClick={undo}
disabled={undoStack.length === 0}
className="px-2 py-1 text-xs border border-gray-300 dark:border-gray-600 rounded hover:bg-gray-50 dark:hover:bg-gray-700 disabled:opacity-30"
title="Rueckgaengig (Ctrl+Z)"
>
&#x21A9;
</button>
<button
onClick={redo}
disabled={redoStack.length === 0}
className="px-2 py-1 text-xs border border-gray-300 dark:border-gray-600 rounded hover:bg-gray-50 dark:hover:bg-gray-700 disabled:opacity-30"
title="Wiederholen (Ctrl+Shift+Z)"
>
&#x21AA;
</button>
<div className="w-px h-5 bg-gray-300 dark:bg-gray-600 mx-1" />
{/* Font scale */}
<label className="flex items-center gap-1 text-xs text-gray-600 dark:text-gray-400">
Schrift
<input
type="range" min={30} max={120} value={Math.round(fontScale * 100)}
onChange={e => setFontScale(Number(e.target.value) / 100)}
className="w-20 h-1 accent-teal-600"
/>
<span className="w-8 text-right font-mono">{Math.round(fontScale * 100)}%</span>
</label>
<button
onClick={() => setGlobalBold(b => !b)}
className={`px-2 py-1 text-xs rounded border transition-colors font-bold ${
globalBold
? 'bg-teal-600 text-white border-teal-600'
: 'bg-white dark:bg-gray-700 text-gray-600 dark:text-gray-400 border-gray-300 dark:border-gray-600'
}`}
>
B
</button>
<button
onClick={() => setImageRotation(r => r === 0 ? 180 : 0)}
className={`px-2 py-1 text-xs rounded border transition-colors ${
imageRotation === 180
? 'bg-teal-600 text-white border-teal-600'
: 'bg-white dark:bg-gray-700 text-gray-600 dark:text-gray-400 border-gray-300 dark:border-gray-600'
}`}
title="Bild 180° drehen"
>
180°
</button>
<div className="w-px h-5 bg-gray-300 dark:bg-gray-600 mx-1" />
<button
onClick={saveReconstruction}
disabled={status === 'saving'}
className="px-4 py-1.5 text-xs bg-teal-600 text-white rounded-lg hover:bg-teal-700 disabled:opacity-50 transition-colors font-medium"
>
Speichern
</button>
</div>
</div>
{/* Side-by-side: Original + Overlay */}
<div className="grid grid-cols-2 gap-4">
{/* Left: Original image */}
<div>
<div className="text-xs font-medium text-gray-500 dark:text-gray-400 mb-1">
Originalbild
</div>
<div className="border rounded-lg overflow-hidden dark:border-gray-700 bg-gray-50 dark:bg-gray-900 sticky top-4">
{/* eslint-disable-next-line @next/next/no-img-element */}
<img
src={dewarpedUrl}
alt="Original"
className="w-full h-auto"
onLoad={(e) => {
const img = e.target as HTMLImageElement
setImageNaturalSize({ w: img.naturalWidth, h: img.naturalHeight })
}}
/>
</div>
</div>
{/* Right: Reconstructed overlay */}
<div>
<div className="text-xs font-medium text-gray-500 dark:text-gray-400 mb-1">
Rekonstruktion ({cells.length} Zellen)
</div>
<div className="border border-gray-200 dark:border-gray-700 rounded-lg overflow-hidden bg-white">
<div
ref={reconRef}
className="relative"
style={{ aspectRatio: `${imgW} / ${imgH}` }}
>
{/* Row lines */}
{rows.map((row, i) => (
<div
key={`row-${i}`}
className="absolute left-0 right-0 border-t border-gray-300/50"
style={{ top: `${(row.y / imgH) * 100}%` }}
/>
))}
{/* Pixel-positioned words / editable inputs */}
{cells.map((cell) => {
const displayText = getDisplayText(cell)
const edited = isEdited(cell)
const wordPos = cellWordPositions.get(cell.cellId)
const bboxPct = cell.bboxPct
const cellHeightPx = containerH * (bboxPct.h / 100)
// Pixel-analysed: render word-groups at detected positions
if (wordPos && wordPos.length > 0) {
return wordPos.map((wp, i) => {
const autoFontPx = cellHeightPx * wp.fontRatio * fontScale
const fs = Math.max(6, autoFontPx)
if (wordPos.length > 1) {
return (
<span
key={`${cell.cellId}_wp_${i}`}
className="absolute leading-none pointer-events-none select-none"
style={{
left: `${wp.xPct}%`,
top: `${bboxPct.y}%`,
width: `${wp.wPct}%`,
height: `${bboxPct.h}%`,
fontSize: `${fs}px`,
fontWeight: globalBold ? 'bold' : 'normal',
fontFamily: "'Liberation Sans', Arial, sans-serif",
display: 'flex',
alignItems: 'center',
whiteSpace: 'nowrap',
overflow: 'visible',
color: '#1a1a1a',
}}
>
{wp.text}
</span>
)
}
return (
<div key={`${cell.cellId}_wp_${i}`} className="absolute group" style={{
left: `${wp.xPct}%`,
top: `${bboxPct.y}%`,
width: `${wp.wPct}%`,
height: `${bboxPct.h}%`,
}}>
<input
id={`cell-${cell.cellId}`}
type="text"
value={displayText}
onChange={(e) => handleTextChange(cell.cellId, e.target.value)}
onKeyDown={(e) => handleKeyDown(e, cell.cellId)}
className={`w-full h-full bg-transparent border-0 outline-none px-0 transition-colors ${
edited ? 'bg-green-50/30' : ''
}`}
style={{
fontSize: `${fs}px`,
fontWeight: globalBold ? 'bold' : 'normal',
fontFamily: "'Liberation Sans', Arial, sans-serif",
lineHeight: '1',
color: '#1a1a1a',
}}
title={`${cell.cellId} (${cell.colType})`}
/>
{edited && (
<button
onClick={() => resetCell(cell.cellId)}
className="absolute -top-1 -right-1 w-4 h-4 bg-red-500 text-white rounded-full text-[9px] leading-none opacity-0 group-hover:opacity-100 transition-opacity flex items-center justify-center"
title="Zuruecksetzen"
>
&times;
</button>
)}
</div>
)
})
}
// Fallback: no pixel data — single input at cell bbox
if (!cell.text) return null
const fontSize = Math.max(6, cellHeightPx * fontScale)
return (
<div key={cell.cellId} className="absolute group" style={{
left: `${bboxPct.x}%`,
top: `${bboxPct.y}%`,
width: `${bboxPct.w}%`,
height: `${bboxPct.h}%`,
}}>
<input
id={`cell-${cell.cellId}`}
type="text"
value={displayText}
onChange={(e) => handleTextChange(cell.cellId, e.target.value)}
onKeyDown={(e) => handleKeyDown(e, cell.cellId)}
className={`w-full h-full bg-transparent border-0 outline-none px-0 transition-colors ${
edited ? 'bg-green-50/30' : ''
}`}
style={{
fontSize: `${fontSize}px`,
fontWeight: globalBold ? 'bold' : 'normal',
fontFamily: "'Liberation Sans', Arial, sans-serif",
lineHeight: '1',
color: '#1a1a1a',
}}
title={`${cell.cellId} (${cell.colType})`}
/>
{edited && (
<button
onClick={() => resetCell(cell.cellId)}
className="absolute -top-1 -right-1 w-4 h-4 bg-red-500 text-white rounded-full text-[9px] leading-none opacity-0 group-hover:opacity-100 transition-opacity flex items-center justify-center"
title="Zuruecksetzen"
>
&times;
</button>
)}
</div>
)
})}
</div>
</div>
</div>
</div>
{/* Bottom action */}
<div className="flex justify-end">
<button
onClick={() => {
if (changedCount > 0) {
saveReconstruction()
} else {
onNext()
}
}}
className="px-6 py-2.5 bg-teal-600 text-white rounded-lg hover:bg-teal-700 transition-colors font-medium text-sm"
>
{changedCount > 0 ? 'Speichern & Fertig' : 'Fertig'}
</button>
</div>
</div>
)
}

View File

@@ -0,0 +1,185 @@
import { useEffect, useState } from 'react'
import type { GridCell } from '@/app/(admin)/ai/ocr-overlay/types'
export interface WordPosition {
xPct: number
wPct: number
text: string
fontRatio: number
}
/**
* Analyse dark-pixel clusters on an image to determine
* the exact horizontal position & auto-font-size of word groups in each cell.
*
* When rotation=180, the image is rotated 180° before pixel analysis.
* Cell coordinates are transformed to the rotated space for reading,
* and cluster positions are mirrored back to the original coordinate system.
*
* Returns a Map<cell_id, WordPosition[]>.
*/
export function usePixelWordPositions(
imageUrl: string,
cells: GridCell[],
active: boolean,
rotation: 0 | 180 = 0,
): Map<string, WordPosition[]> {
const [cellWordPositions, setCellWordPositions] = useState<Map<string, WordPosition[]>>(new Map())
useEffect(() => {
if (!active || cells.length === 0 || !imageUrl) return
const img = new Image()
img.crossOrigin = 'anonymous'
img.onload = () => {
const imgW = img.naturalWidth
const imgH = img.naturalHeight
const canvas = document.createElement('canvas')
canvas.width = imgW
canvas.height = imgH
const ctx = canvas.getContext('2d')
if (!ctx) return
if (rotation === 180) {
ctx.translate(imgW, imgH)
ctx.rotate(Math.PI)
ctx.drawImage(img, 0, 0)
ctx.setTransform(1, 0, 0, 1, 0, 0)
} else {
ctx.drawImage(img, 0, 0)
}
const refFontSize = 40
const fontFam = "'Liberation Sans', Arial, sans-serif"
ctx.font = `${refFontSize}px ${fontFam}`
const positions = new Map<string, WordPosition[]>()
for (const cell of cells) {
if (!cell.bbox_pct || !cell.text) continue
const groups = cell.text.split(/\s{3,}/).map(s => s.trim()).filter(Boolean)
let cx: number, cy: number
const cw = Math.round(cell.bbox_pct.w / 100 * imgW)
const ch = Math.round(cell.bbox_pct.h / 100 * imgH)
if (rotation === 180) {
cx = Math.round((100 - cell.bbox_pct.x - cell.bbox_pct.w) / 100 * imgW)
cy = Math.round((100 - cell.bbox_pct.y - cell.bbox_pct.h) / 100 * imgH)
} else {
cx = Math.round(cell.bbox_pct.x / 100 * imgW)
cy = Math.round(cell.bbox_pct.y / 100 * imgH)
}
if (cw <= 0 || ch <= 0) continue
if (cx < 0) cx = 0
if (cy < 0) cy = 0
if (cx + cw > imgW || cy + ch > imgH) continue
const imageData = ctx.getImageData(cx, cy, cw, ch)
const proj = new Float32Array(cw)
for (let y = 0; y < ch; y++) {
for (let x = 0; x < cw; x++) {
const idx = (y * cw + x) * 4
const lum = 0.299 * imageData.data[idx] + 0.587 * imageData.data[idx + 1] + 0.114 * imageData.data[idx + 2]
if (lum < 128) proj[x]++
}
}
const threshold = Math.max(1, ch * 0.03)
const minGap = Math.max(5, Math.round(cw * 0.02))
let clusters: { start: number; end: number }[] = []
let inCluster = false
let clStart = 0
let gap = 0
for (let x = 0; x < cw; x++) {
if (proj[x] >= threshold) {
if (!inCluster) { clStart = x; inCluster = true }
gap = 0
} else if (inCluster) {
gap++
if (gap > minGap) {
clusters.push({ start: clStart, end: x - gap })
inCluster = false
gap = 0
}
}
}
if (inCluster) clusters.push({ start: clStart, end: cw - 1 - gap })
if (clusters.length === 0) continue
if (rotation === 180) {
clusters = clusters.map(c => ({
start: cw - 1 - c.end,
end: cw - 1 - c.start,
})).reverse()
}
const wordPos: WordPosition[] = []
if (groups.length <= 1) {
const firstCl = clusters[0]
const lastCl = clusters[clusters.length - 1]
const clusterW = lastCl.end - firstCl.start + 1
const measured = ctx.measureText(cell.text.trim())
const autoFontPx = refFontSize * (clusterW / measured.width)
const fontRatio = Math.min(autoFontPx / ch, 1.0)
wordPos.push({
xPct: cell.bbox_pct.x + (firstCl.start / cw) * cell.bbox_pct.w,
wPct: ((lastCl.end - firstCl.start + 1) / cw) * cell.bbox_pct.w,
text: cell.text.trim(),
fontRatio,
})
} else if (clusters.length >= groups.length) {
for (let i = 0; i < groups.length; i++) {
const cl = clusters[i]
const clusterW = cl.end - cl.start + 1
const measured = ctx.measureText(groups[i])
const autoFontPx = refFontSize * (clusterW / measured.width)
const fontRatio = Math.min(autoFontPx / ch, 1.0)
wordPos.push({
xPct: cell.bbox_pct.x + (cl.start / cw) * cell.bbox_pct.w,
wPct: ((cl.end - cl.start + 1) / cw) * cell.bbox_pct.w,
text: groups[i],
fontRatio,
})
}
} else {
continue
}
positions.set(cell.cell_id, wordPos)
}
// Normalise: find the most common fontRatio (mode) and apply it to all
const allRatios: number[] = []
for (const wps of positions.values()) {
for (const wp of wps) allRatios.push(wp.fontRatio)
}
if (allRatios.length > 0) {
const buckets = new Map<number, number>()
for (const r of allRatios) {
const key = Math.round(r * 50) / 50
buckets.set(key, (buckets.get(key) || 0) + 1)
}
let modeRatio = allRatios[0]
let modeCount = 0
for (const [ratio, count] of buckets) {
if (count > modeCount) { modeRatio = ratio; modeCount = count }
}
for (const wps of positions.values()) {
for (const wp of wps) wp.fontRatio = modeRatio
}
}
setCellWordPositions(positions)
}
img.src = imageUrl
}, [active, cells, imageUrl, rotation])
return cellWordPositions
}

View File

@@ -150,6 +150,15 @@ export const navigation: NavCategory[] = [
audience: ['Entwickler', 'Data Scientists'],
subgroup: 'KI-Werkzeuge',
},
{
id: 'ocr-overlay',
name: 'OCR Overlay',
href: '/ai/ocr-overlay',
description: 'Ganzseitige Overlay-Rekonstruktion',
purpose: 'Arbeitsblatt ohne Spaltenerkennung direkt als Overlay rekonstruieren. Vereinfachte 7-Schritt-Pipeline.',
audience: ['Entwickler'],
subgroup: 'KI-Werkzeuge',
},
{
id: 'test-quality',
name: 'Test Quality (BQAS)',