feat: Persistente Sessions (PostgreSQL) + Spaltenerkennung (Step 3)

Sessions werden jetzt in PostgreSQL gespeichert statt in-memory.
Neue Session-Liste mit Name, Datum, Schritt. Sessions ueberleben
Browser-Refresh und Container-Neustart. Step 3 nutzt analyze_layout()
fuer automatische Spaltenerkennung mit farbigem Overlay.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-02-26 22:16:37 +01:00
parent 09b820efbe
commit aa06ae0f61
9 changed files with 1233 additions and 130 deletions

View File

@@ -1,6 +1,6 @@
'use client'
import { useState } from 'react'
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'
@@ -10,11 +10,18 @@ import { StepWordRecognition } from '@/components/ocr-pipeline/StepWordRecogniti
import { StepCoordinates } from '@/components/ocr-pipeline/StepCoordinates'
import { StepReconstruction } from '@/components/ocr-pipeline/StepReconstruction'
import { StepGroundTruth } from '@/components/ocr-pipeline/StepGroundTruth'
import { PIPELINE_STEPS, type PipelineStep } from './types'
import { PIPELINE_STEPS, type PipelineStep, type SessionListItem } 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 [steps, setSteps] = useState<PipelineStep[]>(
PIPELINE_STEPS.map((s, i) => ({
...s,
@@ -22,6 +29,82 @@ export default function OcrPipelinePage() {
})),
)
// 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/${sid}`)
if (!res.ok) return
const data = await res.json()
setSessionId(sid)
setSessionName(data.name || data.filename || '')
// Determine which step to jump to based on current_step
const dbStep = data.current_step || 1
// Steps: 1=deskew, 2=dewarp, 3=columns, ...
// UI steps are 0-indexed: 0=deskew, 1=dewarp, 2=columns, ...
const uiStep = Math.max(0, dbStep - 1)
setSteps(
PIPELINE_STEPS.map((s, i) => ({
...s,
status: i < uiStep ? 'completed' : i === uiStep ? 'active' : 'pending',
})),
)
setCurrentStep(uiStep)
} catch (e) {
console.error('Failed to open session:', e)
}
}, [])
const deleteSession = useCallback(async (sid: string) => {
try {
await fetch(`${KLAUSUR_API}/api/v1/ocr-pipeline/sessions/${sid}`, { method: 'DELETE' })
setSessions((prev) => prev.filter((s) => s.id !== sid))
if (sessionId === sid) {
setSessionId(null)
setCurrentStep(0)
setSteps(PIPELINE_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}
} catch (e) {
console.error('Failed to delete session:', e)
}
}, [sessionId])
const renameSession = useCallback(async (sid: string, newName: string) => {
try {
await fetch(`${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 handleStepClick = (index: number) => {
if (index <= currentStep || steps[index].status === 'completed') {
setCurrentStep(index)
@@ -43,9 +126,28 @@ export default function OcrPipelinePage() {
const handleDeskewComplete = (sid: string) => {
setSessionId(sid)
// Reload session list to show the new session
loadSessions()
handleNext()
}
const handleNewSession = () => {
setSessionId(null)
setSessionName('')
setCurrentStep(0)
setSteps(PIPELINE_STEPS.map((s, i) => ({ ...s, status: i === 0 ? 'active' : 'pending' })))
}
const stepNames: Record<number, string> = {
1: 'Begradigung',
2: 'Entzerrung',
3: 'Spalten',
4: 'Woerter',
5: 'Koordinaten',
6: 'Rekonstruktion',
7: 'Validierung',
}
const renderStep = () => {
switch (currentStep) {
case 0:
@@ -53,7 +155,7 @@ export default function OcrPipelinePage() {
case 1:
return <StepDewarp sessionId={sessionId} onNext={handleNext} />
case 2:
return <StepColumnDetection />
return <StepColumnDetection sessionId={sessionId} onNext={handleNext} />
case 3:
return <StepWordRecognition />
case 4:
@@ -75,7 +177,7 @@ export default function OcrPipelinePage() {
audience={['Entwickler', 'Data Scientists']}
architecture={{
services: ['klausur-service (FastAPI)', 'OpenCV', 'Tesseract'],
databases: ['In-Memory Sessions'],
databases: ['PostgreSQL Sessions'],
}}
relatedPages={[
{ name: 'OCR Vergleich', href: '/ai/ocr-compare', description: 'Methoden-Vergleich' },
@@ -84,6 +186,97 @@ export default function OcrPipelinePage() {
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
</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 max-h-48 overflow-y-auto">
{sessions.map((s) => (
<div
key={s.id}
className={`flex items-center gap-2 px-3 py-2 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'
}`}
>
<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>
)}
<div className="text-xs text-gray-400 flex gap-2">
<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>
<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>
))}
</div>
)}
</div>
{/* Active session name */}
{sessionId && sessionName && (
<div className="text-sm text-gray-500 dark:text-gray-400">
Aktive Session: <span className="font-medium text-gray-700 dark:text-gray-300">{sessionName}</span>
</div>
)}
<PipelineStepper steps={steps} currentStep={currentStep} onStepClick={handleStepClick} />
<div className="min-h-[400px]">{renderStep()}</div>

View File

@@ -7,14 +7,27 @@ export interface PipelineStep {
status: PipelineStepStatus
}
export interface SessionListItem {
id: string
name: string
filename: string
status: string
current_step: number
created_at: string
updated_at?: string
}
export interface SessionInfo {
session_id: string
filename: string
name?: string
image_width: number
image_height: number
original_image_url: string
current_step?: number
deskew_result?: DeskewResult
dewarp_result?: DewarpResult
column_result?: ColumnResult
}
export interface DeskewResult {
@@ -50,6 +63,24 @@ export interface DewarpGroundTruth {
notes?: string
}
export interface PageRegion {
type: 'column_en' | 'column_de' | 'column_example' | 'header' | 'footer'
x: number
y: number
width: number
height: number
}
export interface ColumnResult {
columns: PageRegion[]
duration_seconds: number
}
export interface ColumnGroundTruth {
is_correct: boolean
notes?: string
}
export const PIPELINE_STEPS: PipelineStep[] = [
{ id: 'deskew', name: 'Begradigung', icon: '📐', status: 'pending' },
{ id: 'dewarp', name: 'Entzerrung', icon: '🔧', status: 'pending' },