{"engine":"Text layer + Tesseract OCR fallback","features":["Modular extractor architecture","Text-layer first (fast, accurate on digital PDFs)","OCR only missing/garbled pages","Document type specific processing","Adjustable page range (FS only)","Per-page console output","Standalone OCR endpoint for full-document capture"],"service":"PKF PDF Document Extractor","status":"running","supported_document_types":{"basic_ocr":{"default_pages":"all","extracts":["Per-page text"],"name":"Basic OCR","ocr_pages":"auto (only when needed)"},"caseware":{"default_pages":"1","extracts":["Entity Name","Year End Date","Report Signing Date"],"name":"CaseWare Audit Working Papers","ocr_pages":"1","supports_images":true},"cpe":{"default_pages":"1","extracts":["Participant Name","Hours","Training Title","Certificate Date"],"name":"CPE Certificates","ocr_pages":"1"},"fs":{"default_pages":"3-8","extraction_modes":{"full":"Extract all fields (client name, FYE, signed date, UEN)","page1_only":"Extract only client name and UEN from first page","signature_only":"Extract only signed date from specified pages (default 3-8, customizable with start_page/end_page)"},"extracts":["Client Name","FYE Date","Signed Date","UEN"],"name":"Financial Statements","ocr_pages":"3-8"},"qc35":{"default_pages":"1-2","extracts":["Client Name","Reporting Year-end","Lockdown Date"],"name":"QC35 Documents","ocr_pages":"1-2"}},"version":"8.0.0 - Modular Architecture"}
