egg/OCR
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test

Browse Source
This commit is contained in:
egg
2025-12-04 18:00:37 +08:00
parent 9437387ef1
commit 8265be1741
22 changed files with 2672 additions and 196 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
frontend/src/pages/ProcessingPage.tsx
View File

@@ -8,14 +8,15 @@ import { Button } from '@/components/ui/button'
import { Badge } from '@/components/ui/badge'
import { useToast } from '@/components/ui/toast'
import { apiClientV2 } from '@/services/apiV2'
import { Play, CheckCircle, FileText, AlertCircle, Clock, Activity, Loader2, Info } from 'lucide-react'
import { Play, CheckCircle, FileText, AlertCircle, Clock, Activity, Loader2 } from 'lucide-react'
import LayoutModelSelector from '@/components/LayoutModelSelector'
import PreprocessingSettings from '@/components/PreprocessingSettings'
import PreprocessingPreview from '@/components/PreprocessingPreview'
import TableDetectionSelector from '@/components/TableDetectionSelector'
import ProcessingTrackSelector from '@/components/ProcessingTrackSelector'
import TaskNotFound from '@/components/TaskNotFound'
import { useTaskValidation } from '@/hooks/useTaskValidation'
import type { LayoutModel, ProcessingOptions, PreprocessingMode, PreprocessingConfig, TableDetectionConfig, DocumentAnalysisResponse } from '@/types/apiV2'
import type { LayoutModel, ProcessingOptions, PreprocessingMode, PreprocessingConfig, TableDetectionConfig, ProcessingTrack } from '@/types/apiV2'
export default function ProcessingPage() {
const { t } = useTranslation()
@@ -56,6 +57,9 @@ export default function ProcessingPage() {
enable_region_detection: true,
})
// Processing track override state (null = use system recommendation)
const [forceTrack, setForceTrack] = useState<ProcessingTrack | null>(null)
// Analyze document to determine if OCR is needed (only for pending tasks)
const { data: documentAnalysis, isLoading: isAnalyzing } = useQuery({
queryKey: ['documentAnalysis', taskId],
@@ -65,16 +69,23 @@ export default function ProcessingPage() {
})
// Determine if preprocessing options should be shown
// Only show for OCR track files (images and non-editable PDFs)
const needsOcrTrack = documentAnalysis?.recommended_track === 'ocr' ||
documentAnalysis?.recommended_track === 'hybrid' ||
!documentAnalysis // Show by default while analyzing
// Show OCR options when:
// 1. User explicitly selected OCR track
// 2. OR system recommends OCR/hybrid track (and user hasn't overridden to direct)
// 3. OR still analyzing (show by default)
const needsOcrTrack = forceTrack === 'ocr' ||
(forceTrack === null && (
documentAnalysis?.recommended_track === 'ocr' ||
documentAnalysis?.recommended_track === 'hybrid' ||
!documentAnalysis
))
// Start OCR processing
const processOCRMutation = useMutation({
mutationFn: () => {
const options: ProcessingOptions = {
use_dual_track: true,
use_dual_track: forceTrack === null, // Only use dual-track auto-detection if not forcing
force_track: forceTrack || undefined, // Pass force_track if user selected one
language: 'ch',
layout_model: layoutModel,
preprocessing_mode: preprocessingMode,
@@ -392,53 +403,14 @@ export default function ProcessingPage() {
</div>
)}
{/* Document Analysis Info */}
{documentAnalysis && (
<Card className={documentAnalysis.recommended_track === 'direct' ? 'border-blue-200 bg-blue-50' : 'border-green-200 bg-green-50'}>
<CardContent className="pt-4">
<div className="flex items-start gap-3">
<Info className={`w-5 h-5 flex-shrink-0 mt-0.5 ${documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}`} />
<div className="flex-1">
{documentAnalysis.recommended_track === 'direct' ? (
<>
<p className="text-sm font-medium text-blue-800">此文件為可編輯 PDF</p>
<p className="text-sm text-blue-700 mt-1">
系統偵測到此 PDF 包含文字圖層，將使用直接文字提取方式處理。
版面偵測和影像前處理設定不適用於此類文件。
</p>
</>
) : (
<>
<p className="text-sm font-medium text-green-800">
{documentAnalysis.is_editable ? '混合文件' : '掃描文件 / 影像'}
</p>
<p className="text-sm text-green-700 mt-1">
{documentAnalysis.reason}
</p>
</>
)}
<div className="flex flex-wrap gap-4 mt-2 text-xs">
<span className={documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}>
處理方式: {documentAnalysis.recommended_track === 'direct' ? '直接提取' : documentAnalysis.recommended_track === 'ocr' ? 'OCR 識別' : '混合處理'}
</span>
{documentAnalysis.page_count && (
<span className={documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}>
頁數: {documentAnalysis.page_count}
</span>
)}
{documentAnalysis.text_coverage !== null && (
<span className={documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}>
文字覆蓋率: {(documentAnalysis.text_coverage * 100).toFixed(1)}%
</span>
)}
<span className={documentAnalysis.recommended_track === 'direct' ? 'text-blue-600' : 'text-green-600'}>
信心度: {(documentAnalysis.confidence * 100).toFixed(0)}%
</span>
</div>
</div>
</div>
</CardContent>
</Card>
{/* Processing Track Selector - Always show after analysis */}
{!isAnalyzing && (
<ProcessingTrackSelector
value={forceTrack}
onChange={setForceTrack}
documentAnalysis={documentAnalysis}
disabled={processOCRMutation.isPending}
/>
)}
{/* OCR Track Options - Only show when document needs OCR */}